diff --git a/RAAspotter.py b/RAAspotter.py
index 5eddeaf2b76b1998b23bbfe580f5ca23e101fe00..3454dcde0eece737425369df722183c5dfce6817 100644
--- a/RAAspotter.py
+++ b/RAAspotter.py
@@ -1,4 +1,7 @@
-import os, re, ssl, sys
+import os
+import re
+import ssl
+import sys
import subprocess
import logging
import requests
@@ -28,421 +31,513 @@ from mastodon import Mastodon
logger = logging.getLogger(__name__)
+
class RAAspotter:
- class RAA:
- url = ""
- date = datetime.datetime(1970, 1, 1)
- date_str = ""
- name = ""
- filename = ""
- sha256 = ""
-
- def __init__(self, url, date, name, filename):
- if not url == "":
- self.url = url
- if not date == "":
- self.date = date
- self.date_str = date.strftime("%d/%m/%Y")
- if not name == "":
- self.name = name
- if not filename == "":
- self.filename = filename
-
- def get_sha256(self):
- if (self.sha256 == ""):
- self.sha256 = hashlib.sha256(self.filename.encode('utf-8')).hexdigest()
- return self.sha256
-
- def __init__(self, data_dir, user_agent=''):
- logger.debug('Initialisation de RAAspotter')
-
- self.session = requests.Session()
- self.data_dir = data_dir
- self.found = False
- self.output_file_path = os.path.dirname(os.path.abspath(__file__))+f'/output_{self.short_code}.log'
- self.sleep_time = 0
- self.tor_enabled = False
- self.tor_max_requests = 0
- self.tor_requests = 0
- self.not_before = datetime.datetime(2024, 1, 1)
- self.smtp_configured = False
- self.mastodon = None
- self.mastodon_prefix = ''
- self.mastodon_suffix = ''
-
- self.update_user_agent(user_agent)
-
- f = open(self.output_file_path,'w')
- f.write('')
- f.close()
-
- def configure_mastodon(self, access_token, instance, mastodon_prefix, mastodon_suffix):
- if access_token and access_token != "" and instance and instance != "":
- self.mastodon = Mastodon(
- access_token=access_token,
- api_base_url=instance
- )
- self.mastodon_prefix = mastodon_prefix
- self.mastodon_suffix = mastodon_suffix
-
- def mastodon_toot(self, content):
- if self.mastodon:
- toot = content
- if not self.mastodon_prefix == '':
- toot = f"{self.mastodon_prefix}\n\n{toot}"
- if not self.mastodon_suffix == '':
- toot = f"{toot}\n\n{self.mastodon_suffix}"
- self.mastodon.toot(toot)
-
- def enable_tor(self, max_requests=0):
- proxies = {
- "http": f"socks5h://127.0.0.1:9050",
- "https": f"socks5h://127.0.0.1:9050",
- }
- self.tor_enabled = True
- self.tor_max_requests = max_requests
- self.tor_requests = 0
- self.session.proxies.update(proxies)
- self.tor_get_new_id()
-
- def disable_tor(self):
- proxies = {}
- self.tor_enabled = False
- self.tor_max_requests = 0
- self.tor_requests = 0
- self.session.proxies.update(proxies)
-
- def tor_get_new_id(self):
- logger.info('Changement d\'identité Tor')
- try:
- controller = Controller.from_port(port = 9051)
- controller.authenticate()
- controller.signal(Signal.NEWNYM)
- time.sleep(5)
- self.tor_requests = 0
- except:
- logger.debug('Impossible de changer d\'identité Tor')
-
- def get_sub_pages(self, page_content, element, host, recursive_until_pdf):
- soup = BeautifulSoup(page_content, 'html.parser')
- sub_pages = []
- for a in soup.select(element):
- if a.get('href'):
- url = f"{host}{a['href']}"
- if recursive_until_pdf:
- sub_page_content = self.get_page(url, 'get').content
- if not self.has_pdf(sub_page_content):
- logger.info(f'{url} ne contient pas de PDF, on récupère ses sous-pages')
- for sub_sub_page in self.get_sub_pages(sub_page_content, element, host, recursive_until_pdf):
- sub_pages.append(sub_sub_page)
- else:
- sub_page = {
- 'url': url,
- 'name': a.get_text().strip()
- }
- sub_pages.append(sub_page)
- else:
- sub_page = {
- 'url': url,
- 'name': a.get_text().strip()
- }
- sub_pages.append(sub_page)
- return sub_pages
-
- def get_sub_pages_with_pager(self, page, sub_page_element, pager_element, host):
- pages = []
- page_content = self.get_page(page, 'get').content
-
- # On initialise le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # On recherche les sous-pages
- sub_pages = soup.select(sub_page_element)
- for sub_page in sub_pages:
- if sub_page.get('href'):
- page = {
- 'url': f"{host}{sub_page['href']}",
- 'name': sub_page.get_text().strip()
+ class RAA:
+ url = ""
+ date = datetime.datetime(1970, 1, 1)
+ date_str = ""
+ name = ""
+ filename = ""
+ sha256 = ""
+
+ def __init__(self, url, date, name, filename):
+ if not url == "":
+ self.url = url
+ if not date == "":
+ self.date = date
+ self.date_str = date.strftime("%d/%m/%Y")
+ if not name == "":
+ self.name = name
+ if not filename == "":
+ self.filename = filename
+
+ def get_sha256(self):
+ if (self.sha256 == ""):
+ self.sha256 = hashlib.sha256(
+ self.filename.encode('utf-8')
+ ).hexdigest()
+ return self.sha256
+
+ def __init__(self, data_dir, user_agent=''):
+ logger.debug('Initialisation de RAAspotter')
+
+ self.session = requests.Session()
+ self.data_dir = data_dir
+ self.found = False
+ self.output_file_path = os.path.dirname(
+ os.path.abspath(__file__)
+ )+f'/output_{self.short_code}.log'
+ self.sleep_time = 0
+ self.tor_enabled = False
+ self.tor_max_requests = 0
+ self.tor_requests = 0
+ self.not_before = datetime.datetime(2024, 1, 1)
+ self.smtp_configured = False
+ self.mastodon = None
+ self.mastodon_prefix = ''
+ self.mastodon_suffix = ''
+
+ self.update_user_agent(user_agent)
+
+ f = open(self.output_file_path, 'w')
+ f.write('')
+ f.close()
+
+ def configure_mastodon(self, access_token, instance, mastodon_prefix,
+ mastodon_suffix):
+ if access_token and access_token != "" and instance and instance != "":
+ self.mastodon = Mastodon(
+ access_token=access_token,
+ api_base_url=instance
+ )
+ self.mastodon_prefix = mastodon_prefix
+ self.mastodon_suffix = mastodon_suffix
+
+ def mastodon_toot(self, content):
+ if self.mastodon:
+ toot = content
+ if not self.mastodon_prefix == '':
+ toot = f"{self.mastodon_prefix}\n\n{toot}"
+ if not self.mastodon_suffix == '':
+ toot = f"{toot}\n\n{self.mastodon_suffix}"
+ self.mastodon.toot(toot)
+
+ def enable_tor(self, max_requests=0):
+ proxies = {
+ "http": f"socks5h://127.0.0.1:9050",
+ "https": f"socks5h://127.0.0.1:9050",
}
- pages.append(page)
-
- # On recherche un pager, et si on le trouve on le suit
- pager = soup.select(pager_element)
- if pager and pager[0] and pager[0].get('href'):
- for sub_page in self.get_sub_pages_with_pager(f"{host}{pager[0]['href']}", sub_page_element, pager_element, host):
- pages.append(sub_page)
-
- return pages
-
- def get_raa_with_pager(self, pages_list, pager_element, host):
- elements = []
- # On parse chaque page passée en paramètre
- for page in pages_list:
- page_content = self.get_page(page, 'get').content
-
- # Pour chaque page, on récupère les PDF
- for raa in self.get_raa_elements(page_content):
- elements.append(raa)
-
- # On regarde également s'il n'y aurait pas un pager
- sub_pages = []
- for sub_page in self.get_sub_pages(page_content, pager_element, host, True):
- sub_pages.append(sub_page['url'])
- for sub_raa in self.get_raa_with_pager(sub_pages, pager_element, host):
- elements.append(sub_raa)
- return elements
-
- def set_sleep_time(self, sleep_time):
- self.sleep_time = sleep_time
-
- def has_pdf(self, page_content):
- elements = []
- soup = BeautifulSoup(page_content, 'html.parser')
- for a in soup.find_all('a', href=True):
- if a['href'].endswith('.pdf'):
- return True
- return False
-
- # On démarre le navigateur
- def get_session(self, url, wait_element=""):
- webdriver_options = webdriver.ChromeOptions()
- webdriver_options.add_argument("--no-sandbox")
- webdriver_options.add_argument("--disable-extensions")
- webdriver_options.add_argument("--disable-gpu")
- webdriver_options.add_argument("--disable-dev-shm-usage")
- webdriver_options.add_argument("--use_subprocess")
- webdriver_options.add_argument("--disable-blink-features=AutomationControlled")
-
- if not self.user_agent == "":
- webdriver_options.add_argument(f"--user-agent={self.user_agent}")
-
- webdriver_options.add_argument("--headless")
- webdriver_options.add_argument("--window-size=1024,768")
- display = Display(visible=False, size=(1024, 768))
- display.start()
-
- browser = webdriver.Chrome(options=webdriver_options)
-
- # Téléchargement de l'URL
- browser.get(url)
-
- if not wait_element == "":
- # On attend que le navigateur ait passé les tests anti-robots et que le contenu s'affiche
- WebDriverWait(browser, 120).until(expected_conditions.presence_of_element_located((By.ID, wait_element)))
- page_content = browser.page_source
-
- # On récupère les cookies du navigateur pour les réutiliser plus tard
- for cookie in browser.get_cookies():
- self.session.cookies.set(cookie['name'], cookie['value'])
-
- # On arrête le navigateur
- browser.quit()
- display.stop()
-
- return page_content
-
- def print_output(self, data):
- print(data)
- data = data.replace('\033[92m', '')
- data = data.replace('\033[0m', '')
- data = data.replace('\033[1m', '')
- f = open(self.output_file_path,'a')
- f.write(data+"\n")
- f.close()
-
- def get_page(self, url, method, data={}):
- try:
- logger.debug(f'Chargement de la page {url}')
- if self.sleep_time > 0:
- time.sleep(self.sleep_time)
-
- page = None
- if method == 'get':
- page = self.session.get(url)
- if method == 'post':
- page = self.session.post(url, data=data)
-
- if page.status_code == 429:
- logger.info(f'Erreur 429 Too Many Requests reçue, temporisation...')
+ self.tor_enabled = True
+ self.tor_max_requests = max_requests
+ self.tor_requests = 0
+ self.session.proxies.update(proxies)
self.tor_get_new_id()
- time.sleep(55)
- return self.get_page(url, method, data)
-
- if self.tor_enabled:
- self.tor_requests+=1
- if self.tor_max_requests>0 and self.tor_requests>self.tor_max_requests:
- self.tor_get_new_id()
-
- return page
- except requests.exceptions.ConnectionError as exc:
- logger.info(f'Erreur de connexion, temporisation...')
- self.tor_get_new_id()
- time.sleep(55)
- return self.get_page(url, method, data)
-
- def update_user_agent(self, user_agent):
- self.user_agent = user_agent
- self.session.headers.update({'User-Agent': self.user_agent})
-
- def download_file(self, raa):
- try:
- os.makedirs(os.path.dirname(f'{self.data_dir}{raa.get_sha256()}.pdf'), exist_ok=True)
- file = self.get_page(raa.url, 'get')
- f = open(f'{self.data_dir}{raa.get_sha256()}.pdf','wb')
- f.write(file.content)
- f.close()
- except (requests.exceptions.ConnectionError, requests.exceptions.ChunkedEncodingError):
- logger.warning(f'ATTENTION: la connexion a été interrompue pendant le téléchargement de {raa.url}, nouvelle tentative...')
- self.download_file(raa)
- except Exception as exc:
- logger.warning(f'ATTENTION: Impossible de télécharger le fichier {raa.url}: {exc}')
-
- def parse_pdf(self, raa, keywords):
- if not os.path.isfile(f'{self.data_dir}{raa.get_sha256()}.pdf'):
- logger.warning(f'ATTENTION: le fichier {raa.get_sha256()}.pdf n\'existe pas')
- else:
- text = ""
- try:
- text = extract_text(f'{self.data_dir}{raa.get_sha256()}.pdf')
- except Exception as exc:
- logger.warning(f'ATTENTION: Impossible d\'extraire le texte du fichier {raa.get_sha256()}.pdf : {exc}')
-
- found = False
- found_keywords = []
- for keyword in keywords:
- if re.search(keyword, text, re.IGNORECASE|re.MULTILINE):
- if not found:
- url = quote(raa.url, safe='/:')
- self.print_output(f'\033[92m{raa.name}\033[0m ({raa.date_str})')
- self.print_output(f'URL : {url}')
- found = True
- self.found = True
- self.print_output(f' Le terme \033[1m{keyword}\033[0m a été trouvé.')
- found_keywords.append(keyword)
-
- # Écrit le texte du PDF dans un fichier texte pour une analyse future, puis supprime le PDF
- f = open(f'{self.data_dir}{raa.get_sha256()}.txt','w')
- f.write(text)
- f.close()
- os.remove(f'{self.data_dir}{raa.get_sha256()}.pdf')
- if found:
- self.print_output('')
- url = quote(raa.url, safe='/:')
- found_keywords_str = ', '.join([str(x) for x in found_keywords])
- self.mastodon_toot(f"{raa.name} ({raa.date_str})\n\nLes termes suivants ont été trouvés : {found_keywords_str}.\n\nURL : {url}")
-
-
- def ocr(self, raa, retry_on_failure=True):
- cmd = [
- 'ocrmypdf',
- '-l', 'eng+fra',
- '--output-type', 'pdfa',
- '--redo-ocr',
- '--skip-big', '500',
- '--invalidate-digital-signatures',
- f'{self.data_dir}{raa.get_sha256()}.pdf',
- f'{self.data_dir}{raa.get_sha256()}.pdf'
- ]
- logger.debug(f'Lancement de ocrmypdf: {cmd}')
- try:
- output = subprocess.check_output(cmd, stderr=subprocess.STDOUT)
- except subprocess.CalledProcessError as exc:
- if exc.returncode == 2 and retry_on_failure:
- logger.warning('ATTENTION : Le fichier n\'est pas un PDF correct, nouvelle tentative de le télécharger')
- if self.tor_enabled:
- self.tor_get_new_id()
- self.download_file(raa)
- self.ocr(raa,False)
- elif (not exc.returncode == 6) and (not exc.returncode == 10):
- logger.warning('ATTENTION : Impossible d\'OCRiser le document', exc.returncode, exc.output)
-
- def parse_raa(self, elements, keywords):
- for raa in elements:
- # Si le fichier n'a pas déjà été parsé et qu'il est postérieur à la date maximale d'analyse,
- # on le télécharge et on le parse
- if (raa.date >= self.not_before) and (not os.path.isfile(f'{self.data_dir}{raa.get_sha256()}.txt')):
- url = quote(raa.url, safe='/:')
- logger.info(f'Nouveau fichier : {raa.name} ({raa.date_str}). URL : {url}')
- self.download_file(raa)
- self.ocr(raa, True)
- self.parse_pdf(raa, keywords)
-
- def get_raa(self, page_content):
- logger.error('Cette fonction doit être surchargée')
-
- def configure_mailer(self, smtp_host, smtp_username, smtp_password,
- smtp_port, smtp_starttls, smtp_ssl, email_from,
- email_to, email_object):
- self.smtp_host = smtp_host
- self.smtp_username = smtp_username
- self.smtp_password = smtp_password
- if smtp_port <= 0:
- self.smtp_port = 587
- else:
- self.smtp_port = int(smtp_port)
- self.smtp_starttls = smtp_starttls
- self.smtp_ssl = smtp_ssl
- self.email_from = email_from
- self.email_to = email_to
- self.email_object = email_object
-
- if smtp_host and smtp_username and smtp_password and email_from and email_to and email_object:
- self.smtp_configured = True
-
- def mailer(self):
- if self.smtp_configured and self.found:
- try:
- message = email.message.EmailMessage()
- message.set_content(open(self.output_file_path).read())
-
- message['Subject'] = self.email_object
- message['From'] = self.email_from
- message['Message-ID'] = email.utils.make_msgid(domain=self.email_from.split('@')[-1])
- message['Date'] = email.utils.formatdate()
-
- context = ssl.create_default_context()
-
- if self.smtp_ssl == True:
- for address in self.email_to.split(','):
- del message['To']
- message['To'] = address
- smtp = smtplib.SMTP_SSL(self.smtp_host, port, context=context)
- if self.smtp_username:
- smtp.login(self.smtp_username, self.smtp_password)
- smtp.send_message(message)
- smtp.quit()
- elif self.smtp_starttls == True:
- for address in self.email_to.split(','):
- del message['To']
- message['To'] = address
- smtp = smtplib.SMTP(self.smtp_host)
- smtp.starttls(context=context)
- if self.smtp_username:
- smtp.login(self.smtp_username, self.smtp_password)
- smtp.send_message(message)
- smtp.quit()
+
+ def disable_tor(self):
+ proxies = {}
+ self.tor_enabled = False
+ self.tor_max_requests = 0
+ self.tor_requests = 0
+ self.session.proxies.update(proxies)
+
+ def tor_get_new_id(self):
+ logger.info('Changement d\'identité Tor')
+ try:
+ controller = Controller.from_port(port=9051)
+ controller.authenticate()
+ controller.signal(Signal.NEWNYM)
+ time.sleep(5)
+ self.tor_requests = 0
+ except Exception as exc:
+ logger.debug(f'Impossible de changer d\'identité Tor: {exc}')
+
+ def get_sub_pages(self, page_content, element, host, recursive_until_pdf):
+ soup = BeautifulSoup(page_content, 'html.parser')
+ sub_pages = []
+ for a in soup.select(element):
+ if a.get('href'):
+ url = f"{host}{a['href']}"
+ if recursive_until_pdf:
+ sub_page_content = self.get_page(url, 'get').content
+ if not self.has_pdf(sub_page_content):
+ logger.info(
+ f'{url} ne contient pas de PDF, on '
+ 'récupère ses sous-pages'
+ )
+ for sub_sub_page in self.get_sub_pages(
+ sub_page_content,
+ element,
+ host,
+ recursive_until_pdf
+ ):
+ sub_pages.append(sub_sub_page)
+ else:
+ sub_page = {
+ 'url': url,
+ 'name': a.get_text().strip()
+ }
+ sub_pages.append(sub_page)
+ else:
+ sub_page = {
+ 'url': url,
+ 'name': a.get_text().strip()
+ }
+ sub_pages.append(sub_page)
+ return sub_pages
+
+ def get_sub_pages_with_pager(self, page, sub_page_element, pager_element,
+ host):
+ pages = []
+ page_content = self.get_page(page, 'get').content
+
+ # On initialise le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # On recherche les sous-pages
+ sub_pages = soup.select(sub_page_element)
+ for sub_page in sub_pages:
+ if sub_page.get('href'):
+ page = {
+ 'url': f"{host}{sub_page['href']}",
+ 'name': sub_page.get_text().strip()
+ }
+ pages.append(page)
+
+ # On recherche un pager, et si on le trouve on le suit
+ pager = soup.select(pager_element)
+ if pager and pager[0] and pager[0].get('href'):
+ for sub_page in self.get_sub_pages_with_pager(
+ f"{host}{pager[0]['href']}",
+ sub_page_element,
+ pager_element,
+ host
+ ):
+ pages.append(sub_page)
+
+ return pages
+
+ def get_raa_with_pager(self, pages_list, pager_element, host):
+ elements = []
+ # On parse chaque page passée en paramètre
+ for page in pages_list:
+ page_content = self.get_page(page, 'get').content
+
+ # Pour chaque page, on récupère les PDF
+ for raa in self.get_raa_elements(page_content):
+ elements.append(raa)
+
+ # On regarde également s'il n'y aurait pas un pager
+ sub_pages = []
+ for sub_page in self.get_sub_pages(
+ page_content,
+ pager_element,
+ host,
+ True
+ ):
+ sub_pages.append(sub_page['url'])
+ for sub_raa in self.get_raa_with_pager(
+ sub_pages,
+ pager_element,
+ host
+ ):
+ elements.append(sub_raa)
+ return elements
+
+ def set_sleep_time(self, sleep_time):
+ self.sleep_time = sleep_time
+
+ def has_pdf(self, page_content):
+ elements = []
+ soup = BeautifulSoup(page_content, 'html.parser')
+ for a in soup.find_all('a', href=True):
+ if a['href'].endswith('.pdf'):
+ return True
+ return False
+
+ # On démarre le navigateur
+ def get_session(self, url, wait_element=""):
+ webdriver_options = webdriver.ChromeOptions()
+ webdriver_options.add_argument("--no-sandbox")
+ webdriver_options.add_argument("--disable-extensions")
+ webdriver_options.add_argument("--disable-gpu")
+ webdriver_options.add_argument("--disable-dev-shm-usage")
+ webdriver_options.add_argument("--use_subprocess")
+ webdriver_options.add_argument(
+ "--disable-blink-features=AutomationControlled"
+ )
+
+ if not self.user_agent == "":
+ webdriver_options.add_argument(f"--user-agent={self.user_agent}")
+
+ webdriver_options.add_argument("--headless")
+ webdriver_options.add_argument("--window-size=1024,768")
+ display = Display(visible=False, size=(1024, 768))
+ display.start()
+
+ browser = webdriver.Chrome(options=webdriver_options)
+
+ # Téléchargement de l'URL
+ browser.get(url)
+
+ if not wait_element == "":
+ # On attend que le navigateur ait passé les tests anti-robots et
+ # que le contenu s'affiche
+ WebDriverWait(browser, 120).until(
+ expected_conditions.presence_of_element_located(
+ (
+ By.ID,
+ wait_element
+ )
+ )
+ )
+ page_content = browser.page_source
+
+ # On récupère les cookies du navigateur pour les réutiliser plus tard
+ for cookie in browser.get_cookies():
+ self.session.cookies.set(cookie['name'], cookie['value'])
+
+ # On arrête le navigateur
+ browser.quit()
+ display.stop()
+
+ return page_content
+
+ def print_output(self, data):
+ print(data)
+ data = data.replace('\033[92m', '')
+ data = data.replace('\033[0m', '')
+ data = data.replace('\033[1m', '')
+ f = open(self.output_file_path, 'a')
+ f.write(data+"\n")
+ f.close()
+
+ def get_page(self, url, method, data={}):
+ try:
+ logger.debug(f'Chargement de la page {url}')
+ if self.sleep_time > 0:
+ time.sleep(self.sleep_time)
+
+ page = None
+ if method == 'get':
+ page = self.session.get(url)
+ if method == 'post':
+ page = self.session.post(url, data=data)
+
+ if page.status_code == 429:
+ logger.info(
+ 'Erreur 429 Too Many Requests reçue, temporisation...'
+ )
+ self.tor_get_new_id()
+ time.sleep(55)
+ return self.get_page(url, method, data)
+
+ if self.tor_enabled:
+ self.tor_requests += 1
+ if self.tor_max_requests > 0 and \
+ self.tor_requests > self.tor_max_requests:
+ self.tor_get_new_id()
+
+ return page
+ except requests.exceptions.ConnectionError as exc:
+ logger.info(f'Erreur de connexion, temporisation...')
+ self.tor_get_new_id()
+ time.sleep(55)
+ return self.get_page(url, method, data)
+
+ def update_user_agent(self, user_agent):
+ self.user_agent = user_agent
+ self.session.headers.update({'User-Agent': self.user_agent})
+
+ def download_file(self, raa):
+ try:
+ os.makedirs(
+ os.path.dirname(
+ f'{self.data_dir}{raa.get_sha256()}.pdf'
+ ),
+ exist_ok=True
+ )
+ file = self.get_page(raa.url, 'get')
+ f = open(f'{self.data_dir}{raa.get_sha256()}.pdf', 'wb')
+ f.write(file.content)
+ f.close()
+ except (requests.exceptions.ConnectionError,
+ requests.exceptions.ChunkedEncodingError):
+ logger.warning(
+ 'ATTENTION: la connexion a été interrompue pendant le '
+ f'téléchargement de {raa.url}, nouvelle tentative...'
+ )
+ self.download_file(raa)
+ except Exception as exc:
+ logger.warning(
+ f'ATTENTION: Impossible de télécharger le fichier {raa.url}: '
+ f'{exc}'
+ )
+
+ def parse_pdf(self, raa, keywords):
+ if not os.path.isfile(f'{self.data_dir}{raa.get_sha256()}.pdf'):
+ logger.warning(
+ f'ATTENTION: le fichier {raa.get_sha256()}.pdf n\'existe pas'
+ )
+ else:
+ text = ""
+ try:
+ text = extract_text(f'{self.data_dir}{raa.get_sha256()}.pdf')
+ except Exception as exc:
+ logger.warning(
+ 'ATTENTION: Impossible d\'extraire le texte du fichier '
+ f'{raa.get_sha256()}.pdf : {exc}'
+ )
+
+ found = False
+ found_keywords = []
+ for keyword in keywords:
+ if re.search(keyword, text, re.IGNORECASE | re.MULTILINE):
+ if not found:
+ url = quote(raa.url, safe='/:')
+ self.print_output(
+ f'\033[92m{raa.name}\033[0m ({raa.date_str})'
+ )
+ self.print_output(f'URL : {url}')
+ found = True
+ self.found = True
+ self.print_output(
+ f' Le terme \033[1m{keyword}\033[0m a été trouvé.'
+ )
+ found_keywords.append(keyword)
+
+ # Écrit le texte du PDF dans un fichier texte pour une analyse
+ # future, puis supprime le PDF
+ f = open(f'{self.data_dir}{raa.get_sha256()}.txt', 'w')
+ f.write(text)
+ f.close()
+ os.remove(f'{self.data_dir}{raa.get_sha256()}.pdf')
+ if found:
+ self.print_output('')
+ url = quote(raa.url, safe='/:')
+ found_keywords_str = ', '.join(
+ [str(x) for x in found_keywords]
+ )
+ self.mastodon_toot(
+ f'{raa.name} ({raa.date_str})\n\nLes termes suivants ont '
+ f'été trouvés : {found_keywords_str}.\n\nURL : {url}'
+ )
+
+ def ocr(self, raa, retry_on_failure=True):
+ cmd = [
+ 'ocrmypdf',
+ '-l', 'eng+fra',
+ '--output-type', 'pdfa',
+ '--redo-ocr',
+ '--skip-big', '500',
+ '--invalidate-digital-signatures',
+ f'{self.data_dir}{raa.get_sha256()}.pdf',
+ f'{self.data_dir}{raa.get_sha256()}.pdf'
+ ]
+ logger.debug(f'Lancement de ocrmypdf: {cmd}')
+ try:
+ output = subprocess.check_output(cmd, stderr=subprocess.STDOUT)
+ except subprocess.CalledProcessError as exc:
+ if exc.returncode == 2 and retry_on_failure:
+ logger.warning(
+ 'ATTENTION : Le fichier n\'est pas un PDF correct, '
+ 'nouvelle tentative de le télécharger'
+ )
+ if self.tor_enabled:
+ self.tor_get_new_id()
+ self.download_file(raa)
+ self.ocr(raa, False)
+ elif (not exc.returncode == 6) and (not exc.returncode == 10):
+ logger.warning(
+ 'ATTENTION : Impossible d\'OCRiser le document',
+ exc.returncode,
+ exc.output
+ )
+
+ def parse_raa(self, elements, keywords):
+ for raa in elements:
+ # Si le fichier n'a pas déjà été parsé et qu'il est postérieur à la
+ # date maximale d'analyse, on le télécharge et on le parse
+ if raa.date >= self.not_before and \
+ not os.path.isfile(
+ f'{self.data_dir}{raa.get_sha256()}.txt'
+ ):
+ url = quote(raa.url, safe='/:')
+ logger.info(
+ f'Nouveau fichier : {raa.name} ({raa.date_str}). URL : '
+ f'{url}'
+ )
+ self.download_file(raa)
+ self.ocr(raa, True)
+ self.parse_pdf(raa, keywords)
+
+ def get_raa(self, page_content):
+ logger.error('Cette fonction doit être surchargée')
+
+ def configure_mailer(self, smtp_host, smtp_username, smtp_password,
+ smtp_port, smtp_starttls, smtp_ssl, email_from,
+ email_to, email_object):
+ self.smtp_host = smtp_host
+ self.smtp_username = smtp_username
+ self.smtp_password = smtp_password
+ if smtp_port <= 0:
+ self.smtp_port = 587
else:
- for address in self.email_to.split(','):
- del message['To']
- message['To'] = address
- smtp = smtplib.SMTP(self.smtp_host)
- if self.smtp_username:
- smtp.login(self.smtp_username, self.smtp_password)
- smtp.send_message(message)
- smtp.quit()
- except Exception as exc:
- logger.warning(f'Impossible d\'envoyer le courrier électronique : {exc}')
-
- # Fonction qui essaie de deviner la date d'un RAA Ã partir de son nom.
- # Utile pour limiter les requêtes lors de l'obtention des RAA à scanner.
- def guess_date(string, regex):
- try:
- search = re.search(regex, string, re.IGNORECASE)
- guessed_date = dateparser.parse(search.group(1))
- if guessed_date == None:
- raise Exception('La date est un objet None')
- else:
- return guessed_date
- except Exception as exc:
- logger.warning(f"Impossible de deviner la date du terme {string} : {exc}")
- return datetime.datetime(9999, 1, 1)
+ self.smtp_port = int(smtp_port)
+ self.smtp_starttls = smtp_starttls
+ self.smtp_ssl = smtp_ssl
+ self.email_from = email_from
+ self.email_to = email_to
+ self.email_object = email_object
+
+ if smtp_host and smtp_username and smtp_password and email_from and \
+ email_to and email_object:
+ self.smtp_configured = True
+
+ def mailer(self):
+ if self.smtp_configured and self.found:
+ try:
+ message = email.message.EmailMessage()
+ message.set_content(open(self.output_file_path).read())
+
+ message['Subject'] = self.email_object
+ message['From'] = self.email_from
+ message['Message-ID'] = email.utils.make_msgid(
+ domain=self.email_from.split('@')[-1]
+ )
+ message['Date'] = email.utils.formatdate()
+
+ context = ssl.create_default_context()
+
+ if self.smtp_ssl is True:
+ for address in self.email_to.split(','):
+ del message['To']
+ message['To'] = address
+ smtp = smtplib.SMTP_SSL(
+ self.smtp_host,
+ port,
+ context=context
+ )
+ if self.smtp_username:
+ smtp.login(self.smtp_username, self.smtp_password)
+ smtp.send_message(message)
+ smtp.quit()
+ elif self.smtp_starttls is True:
+ for address in self.email_to.split(','):
+ del message['To']
+ message['To'] = address
+ smtp = smtplib.SMTP(self.smtp_host)
+ smtp.starttls(context=context)
+ if self.smtp_username:
+ smtp.login(self.smtp_username, self.smtp_password)
+ smtp.send_message(message)
+ smtp.quit()
+ else:
+ for address in self.email_to.split(','):
+ del message['To']
+ message['To'] = address
+ smtp = smtplib.SMTP(self.smtp_host)
+ if self.smtp_username:
+ smtp.login(self.smtp_username, self.smtp_password)
+ smtp.send_message(message)
+ smtp.quit()
+ except Exception as exc:
+ logger.warning(
+ f'Impossible d\'envoyer le courrier électronique : {exc}'
+ )
+
+ # Fonction qui essaie de deviner la date d'un RAA Ã partir de son nom.
+ # Utile pour limiter les requêtes lors de l'obtention des RAA à scanner.
+ def guess_date(string, regex):
+ try:
+ search = re.search(regex, string, re.IGNORECASE)
+ guessed_date = dateparser.parse(search.group(1))
+ if guessed_date is None:
+ raise Exception('La date est un objet None')
+ else:
+ return guessed_date
+ except Exception as exc:
+ logger.warning(
+ f'Impossible de deviner la date du terme {string} : {exc}'
+ )
+ return datetime.datetime(9999, 1, 1)
diff --git a/RAAspotter_ppparis.py b/RAAspotter_ppparis.py
index f2ebb8b69deb0afd52212d7cd23831069947b6b9..d605eb39fb541761c086552729f5277900b97f2f 100644
--- a/RAAspotter_ppparis.py
+++ b/RAAspotter_ppparis.py
@@ -5,50 +5,60 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_ppparis(RAAspotter):
- # Config
- __HOST = 'https://www.prefecturedepolice.interieur.gouv.fr'
- __RAA_PAGE = f'{__HOST}/actualites-et-presse/arretes/accueil-arretes'
- __WAIT_ELEMENT = 'block-decree-list-block'
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
- full_name = 'Préfecture de police de Paris'
- short_code = 'ppparis'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_ppparis')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- page_content = self.get_session()
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
- self.mailer()
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
- for a in soup.find_all('a', href=True):
- if a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = 'https://www.prefecturedepolice.interieur.gouv.fr'+a['href']
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').get_text()
- date = datetime.datetime.strptime(a.find('div', class_="field--type-datetime").get_text().strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
-
- def get_session(self):
- return super().get_session(self.__RAA_PAGE, self.__WAIT_ELEMENT)
+ # Config
+ __HOST = 'https://www.prefecturedepolice.interieur.gouv.fr'
+ __RAA_PAGE = f'{__HOST}/actualites-et-presse/arretes/accueil-arretes'
+ __WAIT_ELEMENT = 'block-decree-list-block'
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 ' \
+ '(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
+ full_name = 'Préfecture de police de Paris'
+ short_code = 'ppparis'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_ppparis')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ page_content = self.get_session()
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
+ self.mailer()
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le
+ # parse
+ for a in soup.find_all('a', href=True):
+ if a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = 'https://www.prefecturedepolice.interieur.gouv.fr' \
+ + a['href']
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').get_text()
+ date = datetime.datetime.strptime(
+ a.find(
+ 'div',
+ class_="field--type-datetime"
+ ).get_text().strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
+
+ def get_session(self):
+ return super().get_session(self.__RAA_PAGE, self.__WAIT_ELEMENT)
diff --git a/RAAspotter_pref04.py b/RAAspotter_pref04.py
index 118afb5f92197d0f9f9d260624cb356ce1d1c985..f4953fe9010f29a311711abfb93e12b2120d1481 100644
--- a/RAAspotter_pref04.py
+++ b/RAAspotter_pref04.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,52 +6,72 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref04(RAAspotter):
- # Config
- __HOST = 'https://www.alpes-de-haute-provence.gouv.fr'
- __RAA_PAGE = f'{__HOST}/Publications/Publications-administratives-et-legales/Recueil-des-Actes-Administratifs'
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture des Alpes-de-Haute-Provence'
- short_code = 'pref04'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref04')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- pages = []
- page_content = self.get_page(self.__RAA_PAGE, 'get').content
- for sub_page in self.get_sub_pages(page_content, 'div.fr-card__body div.fr-card__content h2.fr-card__title a', self.__HOST, False):
- if RAAspotter.guess_date(sub_page['name'], '([0-9]{4}).*').year >= self.not_before.year:
- sub_page_content = self.get_page(sub_page['url'], 'get').content
- raa_elements = self.get_raa_elements(sub_page_content)
- self.parse_raa(raa_elements, keywords.split(','))
-
- self.mailer()
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.alpes-de-haute-provence.gouv.fr'
+ __RAA_PAGE = f'{__HOST}/Publications/Publications-administratives-et-'\
+ 'legales/Recueil-des-Actes-Administratifs'
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 '\
+ 'Firefox/115.0'
+ full_name = 'Préfecture des Alpes-de-Haute-Provence'
+ short_code = 'pref04'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref04')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ pages = []
+ page_content = self.get_page(self.__RAA_PAGE, 'get').content
+ for sub_page in self.get_sub_pages(
+ page_content,
+ 'div.fr-card__body div.fr-card__content h2.fr-card__title a',
+ self.__HOST,
+ False
+ ):
+ if RAAspotter.guess_date(
+ sub_page['name'],
+ '([0-9]{4}).*'
+ ).year >= self.not_before.year:
+ sub_page_content = self.get_page(
+ sub_page['url'],
+ 'get'
+ ).content
+ raa_elements = self.get_raa_elements(sub_page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
+
+ self.mailer()
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le
+ # parse
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y')
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref06.py b/RAAspotter_pref06.py
index e58f01800428f53f75042c325d08851b38ce7f69..8f8e272a26809bce1f72d0fc914a993d933a21fd 100644
--- a/RAAspotter_pref06.py
+++ b/RAAspotter_pref06.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,91 +6,131 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref06(RAAspotter):
- # Config
- __HOST = 'https://www.alpes-maritimes.gouv.fr'
- __RAA_PAGE = {'2024':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2024/Recueils-mensuels',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2024/Recueils-speciaux',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2024/Recueils-specifiques'],
- '2023':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2023/Recueils-mensuels',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2023/Recueils-speciaux',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2023/Recueils-specifiques'],
- '2022':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2022/Recueils-mensuels',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2022/Recueils-speciaux',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2022/Recueils-specifiques'],
- '2021':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2021/Recueils-mensuels',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2021/Recueils-speciaux',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2021/Recueils-specifiques'],
- '2020':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2020/Recueils-mensuels',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2020/Recueils-speciaux',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2020/Recueils-specifiques'],
- '2019':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2019/Recueils-mensuels',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2019/Recueils-speciaux',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2019/Recueils-specifiques']}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture des Alpes-Maritimes'
- short_code = 'pref06'
+ # Config
+ __HOST = 'https://www.alpes-maritimes.gouv.fr'
+ __RAA_PAGE = {
+ '2024': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2024/Recueils-mensuels',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2024/Recueils-speciaux',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2024/Recueils-specifiques'
+ ],
+ '2023': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2023/Recueils-mensuels',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2023/Recueils-speciaux',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2023/Recueils-specifiques'
+ ],
+ '2022': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2022/Recueils-mensuels',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2022/Recueils-speciaux',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2022/Recueils-specifiques'
+ ],
+ '2021': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2021/Recueils-mensuels',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2021/Recueils-speciaux',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2021/Recueils-specifiques'
+ ],
+ '2020': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2020/Recueils-mensuels',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2020/Recueils-speciaux',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2020/Recueils-specifiques'
+ ],
+ '2019': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2019/Recueils-mensuels',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2019/Recueils-speciaux',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
+ '/Annee-2019/Recueils-specifiques'
+ ]
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture des Alpes-Maritimes'
+ short_code = 'pref06'
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(20)
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(20)
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref06')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref06')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
- pages_to_parse = []
- if self.not_before.year <= 2024:
- for page in self.__RAA_PAGE['2024']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2023:
- for page in self.__RAA_PAGE['2023']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2022:
- for page in self.__RAA_PAGE['2022']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2021:
- for page in self.__RAA_PAGE['2021']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2020:
- for page in self.__RAA_PAGE['2020']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2019:
- for page in self.__RAA_PAGE['2019']:
- pages_to_parse.append(page)
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ for page in self.__RAA_PAGE['2024']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2023:
+ for page in self.__RAA_PAGE['2023']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2022:
+ for page in self.__RAA_PAGE['2022']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2021:
+ for page in self.__RAA_PAGE['2021']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2020:
+ for page in self.__RAA_PAGE['2020']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2019:
+ for page in self.__RAA_PAGE['2019']:
+ pages_to_parse.append(page)
- elements = self.get_raa_with_pager(pages_to_parse, ".fr-pagination__link.fr-pagination__link--next", self.__HOST)
- self.parse_raa(elements, keywords.split(','))
- self.mailer()
+ elements = self.get_raa_with_pager(
+ pages_to_parse,
+ ".fr-pagination__link.fr-pagination__link--next",
+ self.__HOST
+ )
+ self.parse_raa(elements, keywords.split(','))
+ self.mailer()
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
- # Pour chaque élément fr-card__content, on cherche sa balise a, et si c'est un PDF on le parse
- cards = soup.find_all('div', class_='fr-card__content')
- for card in cards:
- a = card.find('a')
- if a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
+ # Pour chaque élément fr-card__content, on cherche sa balise a, et si
+ # c'est un PDF on le parse
+ cards = soup.find_all('div', class_='fr-card__content')
+ for card in cards:
+ a = card.find('a')
+ if a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
- url = unquote(url)
- name = a.get_text().strip()
- date = datetime.datetime.strptime(card.find('p', class_='fr-card__detail').get_text().replace('Publié le ', '').strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
+ url = unquote(url)
+ name = a.get_text().strip()
+ date = datetime.datetime.strptime(
+ card.find(
+ 'p',
+ class_='fr-card__detail'
+ ).get_text().replace(
+ 'Publié le ',
+ ''
+ ).strip(), '%d/%m/%Y')
+ filename = url.split('/')[-1]
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref13.py b/RAAspotter_pref13.py
index 0285e12158fcaf26f0f117c4c5aeda29d6dd0011..48fab5cc029197262e1cf60c3630c47d8fb06e54 100644
--- a/RAAspotter_pref13.py
+++ b/RAAspotter_pref13.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,54 +6,69 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref13(RAAspotter):
- # Config
- __HOST = 'https://www.bouches-du-rhone.gouv.fr'
- __RAA_PAGE = [f'{__HOST}/Publications/RAA-et-Archives/RAA-2024',
- f'{__HOST}/Publications/RAA-et-Archives/RAA-2023',
- f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2022',
- f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2021',
- f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2020',
- f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2019']
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
- full_name = 'Préfecture des Bouches-du-Rhône'
- short_code = 'pref13'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref13')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- for raa_page in self.__RAA_PAGE:
- page_content = self.get_page(raa_page, 'get').content
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
-
- self.mailer()
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.bouches-du-rhone.gouv.fr'
+ __RAA_PAGE = [
+ f'{__HOST}/Publications/RAA-et-Archives/RAA-2024',
+ f'{__HOST}/Publications/RAA-et-Archives/RAA-2023',
+ f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-'
+ 'Rhone/RAA-2022',
+ f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-'
+ 'Rhone/RAA-2021',
+ f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-'
+ 'Rhone/RAA-2020',
+ f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-'
+ 'Rhone/RAA-2019'
+ ]
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 ' \
+ '(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
+ full_name = 'Préfecture des Bouches-du-Rhône'
+ short_code = 'pref13'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref13')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ for raa_page in self.__RAA_PAGE:
+ page_content = self.get_page(raa_page, 'get').content
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
+
+ self.mailer()
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le
+ # parse
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref34.py b/RAAspotter_pref34.py
index 768143573be4bc319da4cf81d604532cdb6cf1fa..f52c5312e44ada4d5e0c7beb9cdfb60f38b0c58f 100644
--- a/RAAspotter_pref34.py
+++ b/RAAspotter_pref34.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,68 +6,84 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref34(RAAspotter):
- # Config
- __HOST = 'https://www.herault.gouv.fr'
- __RAA_PAGE = {'2024': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2024',
- '2023': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2023',
- '2022': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2022',
- '2021': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2021',
- '2020': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2020',
- '2019': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Archives/Recueil-des-actes-administratifs-2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
- full_name = 'Préfecture de l\'Hérault'
- short_code = 'pref34'
+ # Config
+ __HOST = 'https://www.herault.gouv.fr'
+ __RAA_PAGE = {
+ '2024': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2024',
+ '2023': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2023',
+ '2022': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2022',
+ '2021': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2021',
+ '2020': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2020',
+ '2019': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/Archives/Recueil-des-actes-administratifs-2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 ' \
+ '(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
+ full_name = 'Préfecture de l\'Hérault'
+ short_code = 'pref34'
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref34')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref34')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
- for raa_page in pages_to_parse:
- page_content = self.get_page(raa_page, 'get').content
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(raa_page, 'get').content
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
- self.mailer()
+ self.mailer()
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
- # On récupère chaque balise a
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
+ # On récupère chaque balise a
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref35.py b/RAAspotter_pref35.py
index 6d18b4fc6c68b0d7c950e4615f6260ade454ceb2..8e16411f384f91410b063a4089b8ff5cfe36db31 100644
--- a/RAAspotter_pref35.py
+++ b/RAAspotter_pref35.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,54 +6,76 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref35(RAAspotter):
- # Config
- __HOST = 'https://www.ille-et-vilaine.gouv.fr'
- __RAA_PAGE = [f'{__HOST}/Publications/Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2024',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-des-recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2023',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-des-recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2022',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-des-recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2021',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-des-recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2020',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-des-recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2019']
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
- full_name = 'Préfecture d\'Ille-et-Vilaine'
- short_code = 'pref35'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref35')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- for raa_page in self.__RAA_PAGE:
- page_content = self.get_page(raa_page, 'get').content
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
-
- self.mailer()
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
- for a in soup.find_all('a', href=True, class_='fr-link--download'):
- if a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.ille-et-vilaine.gouv.fr'
+ __RAA_PAGE = [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs/Recueil-des-'
+ 'actes-administratifs-2024',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-'
+ 'des-recueils-des-actes-administratifs/Recueil-des-actes-'
+ 'administratifs-2023',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-'
+ 'des-recueils-des-actes-administratifs/Recueil-des-actes-'
+ 'administratifs-2022',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-'
+ 'des-recueils-des-actes-administratifs/Recueil-des-actes-'
+ 'administratifs-2021',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-'
+ 'des-recueils-des-actes-administratifs/Recueil-des-actes-'
+ 'administratifs-2020',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs/Archives-'
+ 'des-recueils-des-actes-administratifs/Recueil-des-actes-'
+ 'administratifs-2019'
+ ]
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 ' \
+ '(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
+ full_name = 'Préfecture d\'Ille-et-Vilaine'
+ short_code = 'pref35'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref35')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ for raa_page in self.__RAA_PAGE:
+ page_content = self.get_page(raa_page, 'get').content
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
+
+ self.mailer()
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le
+ # parse
+ for a in soup.find_all('a', href=True, class_='fr-link--download'):
+ if a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref38.py b/RAAspotter_pref38.py
index 8b5123ac32d751af6042511f9c7be1d78d1c632c..42a521a93b2cd6e22d67003ea8b950d0b745f8dc 100644
--- a/RAAspotter_pref38.py
+++ b/RAAspotter_pref38.py
@@ -1,4 +1,4 @@
-import os, sys, re
+import os
import datetime
import logging
@@ -9,81 +9,120 @@ from RAAspotter import RAAspotter
logger = logging.getLogger(__name__)
+
class RAAspotter_pref38(RAAspotter):
- # Config
- __HOST = 'https://www.isere.gouv.fr'
- __RAA_PAGE = {'2024': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2024',
- '2023': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2023',
- '2022': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2022',
- '2021': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Archives-des-recueils-des-actes-administratifs-de-la-prefecture-de-l-Isere-2021/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2021',
- '2020': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Archives-des-recueils-des-actes-administratifs-de-la-prefecture-de-l-Isere-2020/Recueils-des-Actes-Administratifs-de-la-Prefecture-de-l-Isere-2020',
- '2019': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Archives-des-Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2019/Archives-des-Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture de l\'Isère'
- short_code = 'pref38'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(20)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref38')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
-
- for raa_page in pages_to_parse:
- page_content = self.get_page(raa_page, 'get').content
- raa_elements = self.get_raa_elements(page_content, raa_page)
- self.parse_raa(raa_elements, keywords.split(','))
- self.mailer()
-
- def get_raa_elements(self, page_content, raa_page):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # On récupère le select qui contient la liste des RAA
- select_list = soup.select('select#-liste-docs')[0]
- # On analyse chaque résultat
- for option in select_list.find_all('option'):
- if not option['value'] == "":
- # On estime la date à partir du nom de fichier
- guessed_date = RAAspotter.guess_date(option['title'], '.* n°[ 0-9]* du ([0-9]*(?:er)? [a-zéû]* [0-9]*)')
-
- # Si la date estimée correspond à la plage d'analyse, on demande au serveur les détails du RAA
- if guessed_date >= self.not_before:
- page_content = self.get_page(raa_page, 'post', {'-liste-docs':option['value']}).content
- # On parse la page de détails pour obtenir les propriétés du RAA
- soup = BeautifulSoup(page_content, 'html.parser')
- a = soup.select('div.liste_deroulante a.fr-link.fr-link--download')[0]
-
- # Si la page contient une balise a qui renvoie vers un pdf, c'est qu'on a obtenu les détails du RAA demandé, donc on le parse
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.isere.gouv.fr'
+ __RAA_PAGE = {
+ '2024': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2024',
+ '2023': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2023',
+ '2022': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Archives/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-'
+ 'Isere-2022',
+ '2021': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Archives/Archives-des-recueils-des-actes-administratifs-de-la-'
+ 'prefecture-de-l-Isere-2021/Recueils-des-Actes-Administratifs-de-la-'
+ 'prefecture-de-l-Isere-2021',
+ '2020': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Archives/Archives-des-recueils-des-actes-administratifs-de-la-'
+ 'prefecture-de-l-Isere-2020/Recueils-des-Actes-Administratifs-de-la-'
+ 'Prefecture-de-l-Isere-2020',
+ '2019': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Archives/Archives-des-Recueils-des-Actes-Administratifs-de-la-'
+ 'prefecture-de-l-Isere-2019/Archives-des-Recueils-des-Actes-'
+ 'Administratifs-de-la-prefecture-de-l-Isere-2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture de l\'Isère'
+ short_code = 'pref38'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(20)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref38')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
+
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(raa_page, 'get').content
+ raa_elements = self.get_raa_elements(page_content, raa_page)
+ self.parse_raa(raa_elements, keywords.split(','))
+ self.mailer()
+
+ def get_raa_elements(self, page_content, raa_page):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # On récupère le select qui contient la liste des RAA
+ select_list = soup.select('select#-liste-docs')[0]
+ # On analyse chaque résultat
+ for option in select_list.find_all('option'):
+ if not option['value'] == "":
+ # On estime la date à partir du nom de fichier
+ guessed_date = RAAspotter.guess_date(
+ option['title'],
+ '.* n°[ 0-9]* du ([0-9]*(?:er)? [a-zéû]* [0-9]*)'
+ )
+
+ # Si la date estimée correspond à la plage d'analyse, on
+ # demande au serveur les détails du RAA
+ if guessed_date >= self.not_before:
+ page_content = self.get_page(
+ raa_page,
+ 'post',
+ {
+ '-liste-docs': option['value']
+ }
+ ).content
+
+ # On parse la page de détails pour obtenir les propriétés
+ # du RAA
+ soup = BeautifulSoup(page_content, 'html.parser')
+ a = soup.select(
+ 'div.liste_deroulante a.fr-link.fr-link--download'
+ )[0]
+
+ # Si la page contient une balise a qui renvoie vers un pdf,
+ # c'est qu'on a obtenu les détails du RAA demandé, donc
+ # on le parse
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref59.py b/RAAspotter_pref59.py
index e5078d8da090fdd07fe7f87bd69d9f2c9d5b1b36..7911488bbcf06748304f9f38ba0c388bb075bd45 100644
--- a/RAAspotter_pref59.py
+++ b/RAAspotter_pref59.py
@@ -1,4 +1,4 @@
-import os, sys, re
+import os
import datetime
import dateparser
import logging
@@ -10,70 +10,94 @@ from RAAspotter import RAAspotter
logger = logging.getLogger(__name__)
+
class RAAspotter_pref59(RAAspotter):
- # Config
- __HOST = 'https://www.nord.gouv.fr'
- __RAA_PAGE = {'2024': f'{__HOST}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord/2024',
- '2023': f'{__HOST}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord/2023',
- '2022': f'{__HOST}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord/2022',
- '2021': f'{__HOST}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord/2021',
- '2020': f'{__HOST}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord/2020',
- '2019': f'{__HOST}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord/2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture du Nord'
- short_code = 'pref59'
+ # Config
+ __HOST = 'https://www.nord.gouv.fr'
+ __RAA_PAGE = {
+ '2024': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/RAA-du-departement-du-Nord/2024',
+ '2023': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/RAA-du-departement-du-Nord/2023',
+ '2022': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/RAA-du-departement-du-Nord/2022',
+ '2021': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/RAA-du-departement-du-Nord/2021',
+ '2020': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/RAA-du-departement-du-Nord/2020',
+ '2019': f'{__HOST}/Publications/Recueils-des-actes-administratifs'
+ '/RAA-du-departement-du-Nord/2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture du Nord'
+ short_code = 'pref59'
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(20)
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(20)
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref59')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref59')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
- for raa_page in pages_to_parse:
- page_content = self.get_page(raa_page, 'get').content
- sub_pages = self.get_sub_pages(page_content, "div.fr-card__body div.fr-card__content h2.fr-card__title a", self.__HOST, True)
- for sub_page in sub_pages[::-1]:
- sub_page_content = self.get_page(sub_page['url'], 'get').content
- sub_raa_elements = self.get_raa_elements(sub_page_content)
- self.parse_raa(sub_raa_elements, keywords.split(','))
- self.mailer()
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(raa_page, 'get').content
+ sub_pages = self.get_sub_pages(
+ page_content,
+ "div.fr-card__body div.fr-card__content h2.fr-card__title a",
+ self.__HOST,
+ True
+ )
+ for sub_page in sub_pages[::-1]:
+ sub_page_content = self.get_page(
+ sub_page['url'],
+ 'get'
+ ).content
+ sub_raa_elements = self.get_raa_elements(sub_page_content)
+ self.parse_raa(sub_raa_elements, keywords.split(','))
+ self.mailer()
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
- # On récupère chaque balise a
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
+ # On récupère chaque balise a
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref62.py b/RAAspotter_pref62.py
index 7b1767d32a70dae3d36c5648afd71ed6a6460418..c792ff9578f5bb85433f346d4c9cddd24f1b9215 100644
--- a/RAAspotter_pref62.py
+++ b/RAAspotter_pref62.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,86 +6,118 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref62(RAAspotter):
- # Config
- __HOST = 'https://www.pas-de-calais.gouv.fr'
- __RAA_PAGE = {'2024':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs/2024-Recueils-des-actes-administratifs'],
- '2023':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs/2023-Recueils-des-actes-administratifs',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/2023-Recueils-speciaux-des-actes-administratifs'],
- '2022':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs/2022-Recueils-des-Actes-Administratifs',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/2022-Recueils-Speciaux-des-Actes-Administratifs'],
- '2021':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs/2021-Recueils-des-actes-administratifs',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/2021-Recueils-speciaux-des-actes-administratifs'],
- '2020':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs/2020-Recueils-des-actes-administratifs',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/2020-Recueils-speciaux-des-actes-administratifs'],
- '2019':
- [f'{__HOST}/Publications/Recueil-des-actes-administratifs/2019-Recueil-des-actes-administratifs',
- f'{__HOST}/Publications/Recueil-des-actes-administratifs/2019-Recueils-speciaux-des-actes-administratifs']}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture du Pas-de-Calais'
- short_code = 'pref62'
+ # Config
+ __HOST = 'https://www.pas-de-calais.gouv.fr'
+ __RAA_PAGE = {
+ '2024': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2024-Recueils-des-actes-administratifs'
+ ],
+ '2023': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2023-Recueils-des-actes-administratifs',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2023-Recueils-speciaux-des-actes-administratifs'
+ ],
+ '2022': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2022-Recueils-des-Actes-Administratifs',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2022-Recueils-Speciaux-des-Actes-Administratifs'
+ ],
+ '2021': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2021-Recueils-des-actes-administratifs',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2021-Recueils-speciaux-des-actes-administratifs'
+ ],
+ '2020': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2020-Recueils-des-actes-administratifs',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2020-Recueils-speciaux-des-actes-administratifs'
+ ],
+ '2019': [
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2019-Recueil-des-actes-administratifs',
+ f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ '/2019-Recueils-speciaux-des-actes-administratifs'
+ ]
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture du Pas-de-Calais'
+ short_code = 'pref62'
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(20)
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(20)
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref62')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref62')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
- pages_to_parse = []
- if self.not_before.year <= 2024:
- for page in self.__RAA_PAGE['2024']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2023:
- for page in self.__RAA_PAGE['2023']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2022:
- for page in self.__RAA_PAGE['2022']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2021:
- for page in self.__RAA_PAGE['2021']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2020:
- for page in self.__RAA_PAGE['2020']:
- pages_to_parse.append(page)
- if self.not_before.year <= 2019:
- for page in self.__RAA_PAGE['2019']:
- pages_to_parse.append(page)
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ for page in self.__RAA_PAGE['2024']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2023:
+ for page in self.__RAA_PAGE['2023']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2022:
+ for page in self.__RAA_PAGE['2022']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2021:
+ for page in self.__RAA_PAGE['2021']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2020:
+ for page in self.__RAA_PAGE['2020']:
+ pages_to_parse.append(page)
+ if self.not_before.year <= 2019:
+ for page in self.__RAA_PAGE['2019']:
+ pages_to_parse.append(page)
- for raa_page in pages_to_parse:
- page_content = self.get_page(raa_page, 'get').content
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
- self.mailer()
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(
+ raa_page,
+ 'get'
+ ).content
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
+ self.mailer()
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
- # On récupère le div qui contient la liste des RAA
- cards = soup.select('div.fr-downloads-group.fr-downloads-group--bordered')[0]
- # On analyse chaque balise a dans ce div
- for a in cards.find_all('a', href=True):
- if a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
+ # On récupère le div qui contient la liste des RAA
+ cards = soup.select(
+ 'div.fr-downloads-group.fr-downloads-group--bordered'
+ )[0]
+ # On analyse chaque balise a dans ce div
+ for a in cards.find_all('a', href=True):
+ if a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements[::-1]
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements[::-1]
diff --git a/RAAspotter_pref65.py b/RAAspotter_pref65.py
index 77de89a125c6e49e293176ee8593b0f320d414fe..2e5aaa7514609aecb44cf0a520f2ccd50529577b 100644
--- a/RAAspotter_pref65.py
+++ b/RAAspotter_pref65.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,68 +6,85 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref65(RAAspotter):
- # Config
- __HOST = 'https://www.hautes-pyrenees.gouv.fr'
- __RAA_PAGE = {'2024': f'{__HOST}/Publications/Recueil-d-actes-administratifs/RAA-2024',
- '2023': f'{__HOST}/Publications/Recueil-d-actes-administratifs/RAA-2023',
- '2022': f'{__HOST}/Publications/Recueil-d-actes-administratifs/RAA-2022',
- '2021': f'{__HOST}/Publications/Recueil-d-actes-administratifs/RAA-2021',
- '2020': f'{__HOST}/Publications/Recueil-d-actes-administratifs/RAA-2020',
- '2019': f'{__HOST}/Publications/Recueil-d-actes-administratifs/RAA-2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture des Hautes-Pyrénées'
- short_code = 'pref65'
+ # Config
+ __HOST = 'https://www.hautes-pyrenees.gouv.fr'
+ __RAA_PAGE = {
+ '2024': f'{__HOST}/Publications/Recueil-d-actes-administratifs'
+ '/RAA-2024',
+ '2023': f'{__HOST}/Publications/Recueil-d-actes-administratifs'
+ '/RAA-2023',
+ '2022': f'{__HOST}/Publications/Recueil-d-actes-administratifs'
+ '/RAA-2022',
+ '2021': f'{__HOST}/Publications/Recueil-d-actes-administratifs'
+ '/RAA-2021',
+ '2020': f'{__HOST}/Publications/Recueil-d-actes-administratifs'
+ '/RAA-2020',
+ '2019': f'{__HOST}/Publications/Recueil-d-actes-administratifs'
+ '/RAA-2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture des Hautes-Pyrénées'
+ short_code = 'pref65'
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref65')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref65')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
- for raa_page in pages_to_parse:
- page_content = self.get_page(raa_page, 'get').content
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(raa_page, 'get').content
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
- self.mailer()
+ self.mailer()
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
- # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
+ # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le
+ # parse
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref69.py b/RAAspotter_pref69.py
index be16a7dce5f897dc5b7759cabde36610bc6dc6aa..a3c0d8e6c10eb954b0432771349605a3dca09063 100644
--- a/RAAspotter_pref69.py
+++ b/RAAspotter_pref69.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,80 +6,101 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref69(RAAspotter):
- # Config
- __HOST = 'https://www.rhone.gouv.fr'
- __RAA_PAGE = {'2024': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2024',
- '2023': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2023',
- '2022': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2022',
- '2021': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2021',
- '2020': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2020',
- '2019': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture du Rhône'
- short_code = 'pref69'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(20)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref69')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
-
- sub_pages_to_parse = []
-
- for raa_page in pages_to_parse:
- sub_pages = self.get_sub_pages_with_pager(raa_page,
- "div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link",
- "ul.fr-pagination__list li a.fr-pagination__link--next",
- self.__HOST)[::-1]
- for sub_page in sub_pages:
- sub_pages_to_parse.append(sub_page['url'])
-
- elements = []
- for sub_page_to_parse in sub_pages_to_parse:
- page_content = self.get_page(sub_page_to_parse, 'get').content
- for element in self.get_raa_elements(page_content)[::-1]:
- elements.append(element)
-
- self.parse_raa(elements, keywords.split(','))
- self.mailer()
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # On récupère chaque balise a
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.rhone.gouv.fr'
+ __RAA_PAGE = {
+ '2024': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-'
+ 'Rhone-RAA/Recueils-de-2024',
+ '2023': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-'
+ 'Rhone-RAA/Recueils-de-2023',
+ '2022': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-'
+ 'Rhone-RAA/Recueils-de-2022',
+ '2021': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-'
+ 'Rhone-RAA/Recueils-de-2021',
+ '2020': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-'
+ 'Rhone-RAA/Recueils-de-2020',
+ '2019': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-'
+ 'Rhone-RAA/Recueils-de-2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture du Rhône'
+ short_code = 'pref69'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(20)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref69')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
+
+ sub_pages_to_parse = []
+
+ for raa_page in pages_to_parse:
+ sub_pages = self.get_sub_pages_with_pager(
+ raa_page,
+ 'div.fr-card__body div.fr-card__content '
+ 'h2.fr-card__title a.fr-card__link',
+ "ul.fr-pagination__list li a.fr-pagination__link--next",
+ self.__HOST)[::-1]
+ for sub_page in sub_pages:
+ sub_pages_to_parse.append(sub_page['url'])
+
+ elements = []
+ for sub_page_to_parse in sub_pages_to_parse:
+ page_content = self.get_page(
+ sub_page_to_parse,
+ 'get'
+ ).content
+ for element in self.get_raa_elements(page_content)[::-1]:
+ elements.append(element)
+
+ self.parse_raa(elements, keywords.split(','))
+ self.mailer()
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # On récupère chaque balise a
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref83.py b/RAAspotter_pref83.py
index 791d72cb42f4ca56d1df61de4f3628aa5202b47b..7e6d9cf49eca13cbc8d22c1e858e70e122d99b6c 100644
--- a/RAAspotter_pref83.py
+++ b/RAAspotter_pref83.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,82 +6,105 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref83(RAAspotter):
- # Config
- __HOST = 'https://www.var.gouv.fr'
- __RAA_PAGE = {'2024': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2024',
- '2023': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2023',
- '2022': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2022',
- '2021': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2021',
- '2020': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2020',
- '2019': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
- full_name = 'Préfecture du Var'
- short_code = 'pref83'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref83')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
-
- sub_pages_to_parse = []
-
- # Pour chaque année, on cherche les sous-pages de mois
- for raa_page in pages_to_parse:
- sub_pages_to_parse.append(raa_page)
- page_content = self.get_page(raa_page, 'get').content
- month_pages = self.get_sub_pages(
- page_content,
- '.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link div.fr-card__body div.fr-card__content h2.fr-card__title a',
- self.__HOST,
- False
- )[::-1]
- for month_page in month_pages:
- sub_pages_to_parse.append(month_page['url'])
-
- # On parse les pages contenant des RAA
- elements = self.get_raa_with_pager(sub_pages_to_parse[::-1], ".fr-pagination__link.fr-pagination__link--next", self.__HOST)
- self.parse_raa(elements, keywords.split(','))
-
- self.mailer()
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # On récupère chaque section contenant un RAA
- for a in soup.select('div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link.menu-item-link'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.get_text().strip()
- date = datetime.datetime.strptime(a['title'].split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.var.gouv.fr'
+ __RAA_PAGE = {
+ '2024': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2024',
+ '2023': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2023',
+ '2022': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2022',
+ '2021': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2021',
+ '2020': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2020',
+ '2019': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs'
+ '/Recueil-des-actes-administratifs-2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) ' \
+ 'Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture du Var'
+ short_code = 'pref83'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref83')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
+
+ sub_pages_to_parse = []
+
+ # Pour chaque année, on cherche les sous-pages de mois
+ for raa_page in pages_to_parse:
+ sub_pages_to_parse.append(raa_page)
+ page_content = self.get_page(raa_page, 'get').content
+ month_pages = self.get_sub_pages(
+ page_content,
+ '.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link '
+ 'div.fr-card__body '
+ 'div.fr-card__content h2.fr-card__title a',
+ self.__HOST,
+ False
+ )[::-1]
+ for month_page in month_pages:
+ sub_pages_to_parse.append(month_page['url'])
+
+ # On parse les pages contenant des RAA
+ elements = self.get_raa_with_pager(
+ sub_pages_to_parse[::-1],
+ ".fr-pagination__link.fr-pagination__link--next",
+ self.__HOST
+ )
+ self.parse_raa(elements, keywords.split(','))
+
+ self.mailer()
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # On récupère chaque section contenant un RAA
+ cards = soup.select(
+ 'div.fr-card__body div.fr-card__content '
+ 'h2.fr-card__title a.fr-card__link.menu-item-link'
+ )
+ for a in cards:
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.get_text().strip()
+ date = datetime.datetime.strptime(
+ a['title'].split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/RAAspotter_pref976.py b/RAAspotter_pref976.py
index 39b28b6ce8b8c6597b1192601b8ccea7257ff0c2..f06eea57f20c73a51814175bd6ad6860ccf5ce76 100644
--- a/RAAspotter_pref976.py
+++ b/RAAspotter_pref976.py
@@ -1,4 +1,4 @@
-import os, sys
+import os
import datetime
from bs4 import BeautifulSoup
@@ -6,108 +6,137 @@ from urllib.parse import unquote
from RAAspotter import RAAspotter
+
class RAAspotter_pref976(RAAspotter):
- # Config
- __HOST = 'https://www.mayotte.gouv.fr'
- __RAA_PAGE = {'default': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A',
- '2024': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2024',
- '2023': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2023',
- '2022': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2022',
- '2021': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2021',
- '2020': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2020',
- '2019': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2019'}
- __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
- full_name = 'Préfecture de Mayotte'
- short_code = 'pref976'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.__USER_AGENT)
- self.enable_tor(10)
-
- def get_raa(self, keywords):
- self.print_output('RAAspotter_pref976')
- self.print_output(f'Termes recherchés: {keywords}')
- self.print_output('')
-
- pages_to_parse = []
- if self.not_before.year <= 2024:
- pages_to_parse.append(self.__RAA_PAGE['2024'])
- if self.not_before.year <= 2023:
- pages_to_parse.append(self.__RAA_PAGE['2023'])
- if self.not_before.year <= 2022:
- pages_to_parse.append(self.__RAA_PAGE['2022'])
- if self.not_before.year <= 2021:
- pages_to_parse.append(self.__RAA_PAGE['2021'])
- if self.not_before.year <= 2020:
- pages_to_parse.append(self.__RAA_PAGE['2020'])
- if self.not_before.year <= 2019:
- pages_to_parse.append(self.__RAA_PAGE['2019'])
-
- sub_pages_to_parse = [self.__RAA_PAGE['default']]
-
- # Pour chaque année, on cherche les sous-pages de mois
- for raa_page in pages_to_parse:
- page_content = self.get_page(raa_page, 'get').content
- month_pages = self.get_sub_pages(
- page_content,
- '.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link div.fr-card__body div.fr-card__content h2.fr-card__title a',
- self.__HOST,
- False
- )[::-1]
-
- # On regarde aussi si sur la page de l'année il n'y aurait pas un RAA mal catégorisé
- for page_to_parse in self.find_raa_card(raa_page):
- sub_pages_to_parse.append(page_to_parse)
-
- # Pour chaque mois, on cherche les pages des RAA
- for month_page in month_pages:
- year = RAAspotter.guess_date(month_page['name'], '(.*)').year
- for page_to_parse in self.find_raa_card(month_page['url'], year):
- sub_pages_to_parse.append(page_to_parse)
-
- # On parse les pages contenant des RAA
- for page in sub_pages_to_parse:
- page_content = self.get_page(page, 'get').content
- raa_elements = self.get_raa_elements(page_content)
- self.parse_raa(raa_elements, keywords.split(','))
- self.mailer()
-
- def find_raa_card(self, page, year=None):
- pages = []
- card_pages = self.get_sub_pages_with_pager(
- page,
- 'div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link',
- 'ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next',
- self.__HOST
- )[::-1]
- for card_page in card_pages:
- # On filtre les pages de RAA ne correspondant pas à la période analysée
- guessed_date = RAAspotter.guess_date(card_page['name'], 'n°[ 0-9]* du ([0-9]*(?:er)? [a-zéû]* [0-9]*)')
- if year:
- guessed_date = guessed_date.replace(year = year)
- if guessed_date >= self.not_before:
- pages.append(card_page['url'])
- return pages
-
- def get_raa_elements(self, page_content):
- elements = []
- # On charge le parser
- soup = BeautifulSoup(page_content, 'html.parser')
-
- # On récupère chaque balise a
- for a in soup.select('a.fr-link.fr-link--download'):
- if a.get('href') and a['href'].endswith('.pdf'):
- if a['href'].startswith('/'):
- url = f"{self.__HOST}{a['href']}"
- else:
- url = a['href']
-
- url = unquote(url)
- name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
- date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
- filename = url.split('/')[-1]
-
- raa = RAAspotter.RAA(url, date, name, filename)
- elements.append(raa)
- return elements
+ # Config
+ __HOST = 'https://www.mayotte.gouv.fr'
+ __RAA_PAGE = {
+ 'default': f'{__HOST}/Publications/Recueil-des-actes-administratifs-'
+ 'R.A.A',
+ '2024': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A'
+ '/RAA-2024',
+ '2023': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A'
+ '/RAA-2023',
+ '2022': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A'
+ '/RAA-2022',
+ '2021': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A'
+ '/RAA-2021',
+ '2020': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A'
+ '/RAA-2020',
+ '2019': f'{__HOST}/Publications/Recueil-des-actes-administratifs-R.A.A'
+ '/RAA-2019'
+ }
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 ' \
+ '(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
+ full_name = 'Préfecture de Mayotte'
+ short_code = 'pref976'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref976')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ pages_to_parse = []
+ if self.not_before.year <= 2024:
+ pages_to_parse.append(self.__RAA_PAGE['2024'])
+ if self.not_before.year <= 2023:
+ pages_to_parse.append(self.__RAA_PAGE['2023'])
+ if self.not_before.year <= 2022:
+ pages_to_parse.append(self.__RAA_PAGE['2022'])
+ if self.not_before.year <= 2021:
+ pages_to_parse.append(self.__RAA_PAGE['2021'])
+ if self.not_before.year <= 2020:
+ pages_to_parse.append(self.__RAA_PAGE['2020'])
+ if self.not_before.year <= 2019:
+ pages_to_parse.append(self.__RAA_PAGE['2019'])
+
+ sub_pages_to_parse = [self.__RAA_PAGE['default']]
+
+ # Pour chaque année, on cherche les sous-pages de mois
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(raa_page, 'get').content
+ month_pages = self.get_sub_pages(
+ page_content,
+ '.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link '
+ 'div.fr-card__body div.fr-card__content '
+ 'h2.fr-card__title a',
+ self.__HOST,
+ False
+ )[::-1]
+
+ # On regarde aussi si sur la page de l'année il n'y aurait pas un
+ # RAA mal catégorisé
+ for page_to_parse in self.find_raa_card(raa_page):
+ sub_pages_to_parse.append(page_to_parse)
+
+ # Pour chaque mois, on cherche les pages des RAA
+ for month_page in month_pages:
+ year = RAAspotter.guess_date(month_page['name'], '(.*)').year
+ for page_to_parse in self.find_raa_card(
+ month_page['url'],
+ year
+ ):
+ sub_pages_to_parse.append(page_to_parse)
+
+ # On parse les pages contenant des RAA
+ for page in sub_pages_to_parse:
+ page_content = self.get_page(page, 'get').content
+ raa_elements = self.get_raa_elements(page_content)
+ self.parse_raa(raa_elements, keywords.split(','))
+ self.mailer()
+
+ def find_raa_card(self, page, year=None):
+ pages = []
+ card_pages = self.get_sub_pages_with_pager(
+ page,
+ 'div.fr-card__body div.fr-card__content h2.fr-card__title '
+ 'a.fr-card__link',
+ 'ul.fr-pagination__list li '
+ 'a.fr-pagination__link.fr-pagination__link--next',
+ self.__HOST
+ )[::-1]
+ for card_page in card_pages:
+ # On filtre les pages de RAA ne correspondant pas à la période
+ # analysée
+ guessed_date = RAAspotter.guess_date(
+ card_page['name'],
+ 'n°[ 0-9]* du ([0-9]*(?:er)? [a-zéû]* [0-9]*)'
+ )
+ if year:
+ guessed_date = guessed_date.replace(year=year)
+ if guessed_date >= self.not_before:
+ pages.append(card_page['url'])
+ return pages
+
+ def get_raa_elements(self, page_content):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # On récupère chaque balise a
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
+ if a['href'].startswith('/'):
+ url = f"{self.__HOST}{a['href']}"
+ else:
+ url = a['href']
+
+ url = unquote(url)
+ name = a.find('span').previous_sibling.replace(
+ 'Télécharger ',
+ ''
+ ).strip()
+ date = datetime.datetime.strptime(
+ a.find('span').get_text().split(' - ')[-1].strip(),
+ '%d/%m/%Y'
+ )
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/cli.py b/cli.py
index 150fbb582b941ac6776af9318d8c428a1bfaa974..995c87adcb3989bf66d9e2d5e413b8241a990106 100755
--- a/cli.py
+++ b/cli.py
@@ -7,7 +7,8 @@ import importlib
from RAAspotter import RAAspotter
# Config
-__KEYWORDS = os.getenv('KEYWORDS') or 'vidéoprotection,caméras,captation,aéronef'
+__KEYWORDS = os.getenv('KEYWORDS') or \
+ 'vidéoprotection,caméras,captation,aéronef'
__DATA_DIR_ROOT = os.path.dirname(os.path.abspath(__file__))+'/data/'
__SMTP_HOSTNAME = os.getenv('SMTP_HOSTNAME') or 'localhost'
__SMTP_USERNAME = os.getenv('SMTP_USERNAME') or ''
@@ -15,120 +16,204 @@ __SMTP_PASSWORD = os.getenv('SMTP_PASSWORD') or ''
__EMAIL_FROM = os.getenv('EMAIL_FROM')
__EMAIL_TO = os.getenv('EMAIL_TO')
if os.getenv('SMTP_PORT'):
- __SMTP_PORT = int(os.getenv('SMTP_PORT'))
+ __SMTP_PORT = int(os.getenv('SMTP_PORT'))
else:
- __SMTP_PORT = 587
+ __SMTP_PORT = 587
if os.getenv('SMTP_STARTTLS'):
- __SMTP_STARTTLS = True
+ __SMTP_STARTTLS = True
else:
- __SMTP_STARTTLS = False
+ __SMTP_STARTTLS = False
if os.getenv('SMTP_SSL'):
- __SMTP_SSL = True
+ __SMTP_SSL = True
else:
- __SMTP_SSL = False
+ __SMTP_SSL = False
if os.getenv('NOT_BEFORE'):
- __NOT_BEFORE = datetime.datetime.strptime(os.getenv('NOT_BEFORE'), '%Y-%m-%d')
+ __NOT_BEFORE = datetime.datetime.strptime(
+ os.getenv('NOT_BEFORE'), '%Y-%m-%d'
+ )
else:
- __NOT_BEFORE = datetime.datetime(2024, 1, 1)
+ __NOT_BEFORE = datetime.datetime(2024, 1, 1)
__MASTODON_ACCESS_TOKEN = os.getenv('MASTODON_ACCESS_TOKEN')
__MASTODON_INSTANCE = os.getenv('MASTODON_INSTANCE')
# Liste des préfectures supportées
available_prefs = [
- 'ppparis',
- 'pref04',
- 'pref06',
- 'pref13',
- 'pref34',
- 'pref35',
- 'pref38',
- 'pref59',
- 'pref62',
- 'pref65',
- 'pref69',
- 'pref83',
- 'pref976'
+ 'ppparis',
+ 'pref04',
+ 'pref06',
+ 'pref13',
+ 'pref34',
+ 'pref35',
+ 'pref38',
+ 'pref59',
+ 'pref62',
+ 'pref65',
+ 'pref69',
+ 'pref83',
+ 'pref976'
]
# Début du script
-parser = argparse.ArgumentParser(prog='cli.py', description='Télécharge les RAA d\'une préfecture donnée et recherche des mots-clés')
-parser.add_argument('-p', '--pref', action='store', help='identifiant de la préfecture', required=True, choices=available_prefs)
-parser.add_argument('-k', '--keywords', action='store', help='liste des termes recherchés, séparés par une virgule (par défaut : vidéoprotection,caméras,captation,aéronef)')
-parser.add_argument('--not-before', action='store', help='n\'analyse pas les RAA datant d\'avant la date indiquée, au format YYYY-MM-DD (par défaut : 2024-01-01)')
-parser.add_argument('--smtp-hostname', action='store', help='nom d\'hôte SMTP (par défaut : localhost)')
-parser.add_argument('--smtp-username', action='store', help='nom d\'utilisateur SMTP (par défaut : vide)')
-parser.add_argument('--smtp-password', action='store', help='mot de passe SMTP (par défaut : vide)')
-parser.add_argument('--smtp-port', action='store', help='port SMTP (par défaut : 587)')
-parser.add_argument('--smtp-starttls', action='store_true', help='connexion SMTP avec STARTTLS')
-parser.add_argument('--smtp-ssl', action='store_true', help='connexion SMTP avec SSL')
-parser.add_argument('-f', '--email-from', action='store', help='adresse de courrier électronique expéditrice des notifications')
-parser.add_argument('-t', '--email-to', action='store', help='adresses de courrier électronique destinataires des notifications (séparées par une virgule)')
+parser = argparse.ArgumentParser(
+ prog='cli.py',
+ description='Télécharge les RAA d\'une préfecture donnée et recherche des '
+ 'mots-clés'
+)
+parser.add_argument(
+ '-p',
+ '--pref',
+ action='store',
+ help='identifiant de la préfecture',
+ required=True,
+ choices=available_prefs
+)
+parser.add_argument(
+ '-k',
+ '--keywords',
+ action='store',
+ help='liste des termes recherchés, séparés par une virgule (par défaut : '
+ 'vidéoprotection,caméras,captation,aéronef)'
+)
+parser.add_argument(
+ '--not-before',
+ action='store',
+ help='n\'analyse pas les RAA datant d\'avant la date indiquée, au format '
+ 'YYYY-MM-DD (par défaut : 2024-01-01)'
+)
+parser.add_argument(
+ '--smtp-hostname',
+ action='store',
+ help='nom d\'hôte SMTP (par défaut : localhost)'
+)
+parser.add_argument(
+ '--smtp-username',
+ action='store',
+ help='nom d\'utilisateur SMTP (par défaut : vide)'
+)
+parser.add_argument(
+ '--smtp-password',
+ action='store',
+ help='mot de passe SMTP (par défaut : vide)'
+)
+parser.add_argument(
+ '--smtp-port',
+ action='store',
+ help='port SMTP (par défaut : 587)'
+)
+parser.add_argument(
+ '--smtp-starttls',
+ action='store_true',
+ help='connexion SMTP avec STARTTLS'
+)
+parser.add_argument(
+ '--smtp-ssl',
+ action='store_true',
+ help='connexion SMTP avec SSL'
+)
+parser.add_argument(
+ '-f',
+ '--email-from',
+ action='store',
+ help='adresse de courrier électronique expéditrice des notifications'
+)
+parser.add_argument(
+ '-t',
+ '--email-to',
+ action='store',
+ help='adresses de courrier électronique destinataires des notifications '
+ '(séparées par une virgule)'
+)
for pref in available_prefs:
- parser.add_argument(f'--{pref}-email-to', action='store', help=f'adresses de courrier électronique destinataires des notifications (séparées par une virgule) uniquement si l\'analyse concerne {pref} (s\'ajoute à celles précisées dans --email-to)')
-
-parser.add_argument('--mastodon-access-token', action='store', help='jeton d\'accès pour publier sur Mastodon (par défaut : vide)')
-parser.add_argument('--mastodon-instance', action='store', help='URL de l\'instance (doit inclure "http://" ou "https://" ; par défaut : vide)')
-parser.add_argument('-v', action='store_true', help='relève le niveau de verbosité à INFO')
-parser.add_argument('-vv', action='store_true', help='relève le niveau de verbosité à DEBUG')
+ parser.add_argument(
+ f'--{pref}-email-to',
+ action='store',
+ help=f'adresses de courrier électronique destinataires des '
+ 'notifications (séparées par une virgule) uniquement si '
+ 'l\'analyse concerne {pref} (s\'ajoute à celles précisées dans '
+ '--email-to)'
+ )
+
+parser.add_argument(
+ '--mastodon-access-token',
+ action='store',
+ help='jeton d\'accès pour publier sur Mastodon (par défaut : vide)'
+)
+parser.add_argument(
+ '--mastodon-instance',
+ action='store',
+ help='URL de l\'instance (doit inclure "http://" ou "https://" ; par '
+ 'défaut : vide)'
+)
+parser.add_argument(
+ '-v',
+ action='store_true',
+ help='relève le niveau de verbosité à INFO'
+)
+parser.add_argument(
+ '-vv',
+ action='store_true',
+ help='relève le niveau de verbosité à DEBUG'
+)
args = parser.parse_args()
if args.v or os.getenv('VERBOSE'):
- logging.basicConfig(level=logging.INFO)
+ logging.basicConfig(level=logging.INFO)
if args.vv or os.getenv('VVERBOSE'):
- logging.basicConfig(level=logging.DEBUG)
+ logging.basicConfig(level=logging.DEBUG)
if args.keywords:
- __KEYWORDS = args.keywords
+ __KEYWORDS = args.keywords
if args.not_before:
- __NOT_BEFORE = datetime.datetime.strptime(args.not_before, '%Y-%m-%d')
+ __NOT_BEFORE = datetime.datetime.strptime(args.not_before, '%Y-%m-%d')
if args.smtp_hostname:
- __SMTP_HOSTNAME = args.smtp_hostname
+ __SMTP_HOSTNAME = args.smtp_hostname
if args.smtp_username:
- __SMTP_USERNAME = args.smtp_username
+ __SMTP_USERNAME = args.smtp_username
if args.smtp_password:
- __SMTP_PASSWORD = args.smtp_password
+ __SMTP_PASSWORD = args.smtp_password
if args.smtp_port:
- __SMTP_PORT = int(args.smtp_port)
+ __SMTP_PORT = int(args.smtp_port)
if args.smtp_starttls:
- __SMTP_STARTTLS = True
+ __SMTP_STARTTLS = True
if args.smtp_ssl:
- __SMTP_SSL = True
+ __SMTP_SSL = True
if args.email_from:
- __EMAIL_FROM = args.email_from
+ __EMAIL_FROM = args.email_from
if args.email_to:
- __EMAIL_TO = args.email_to
+ __EMAIL_TO = args.email_to
if args.mastodon_access_token:
- __MASTODON_ACCESS_TOKEN = args.mastodon_access_token
+ __MASTODON_ACCESS_TOKEN = args.mastodon_access_token
if args.mastodon_instance:
- __MASTODON_INSTANCE = args.mastodon_instance
+ __MASTODON_INSTANCE = args.mastodon_instance
__DATA_DIR = f'{__DATA_DIR_ROOT}{args.pref}/'
-# On calcule la liste des mails à notifier (liste générale EMAIL_TO + liste prefecture EMAIL_TO_PREF**)
+# On calcule la liste des mails à notifier (liste générale EMAIL_TO + liste
+# prefecture EMAIL_TO_PREF**)
__PREF_EMAIL_TO = ''
pref_var_name = f'{args.pref}_EMAIL_TO'.upper()
if os.getenv(pref_var_name):
- __PREF_EMAIL_TO = os.getenv(pref_var_name)
+ __PREF_EMAIL_TO = os.getenv(pref_var_name)
else:
- for arg in vars(args).items():
- if arg[0] == f'{args.pref}_email_to':
- __PREF_EMAIL_TO = arg[1]
+ for arg in vars(args).items():
+ if arg[0] == f'{args.pref}_email_to':
+ __PREF_EMAIL_TO = arg[1]
if __PREF_EMAIL_TO and not __PREF_EMAIL_TO == '':
- __EMAIL_TO = f'{__EMAIL_TO},{__PREF_EMAIL_TO}'
+ __EMAIL_TO = f'{__EMAIL_TO},{__PREF_EMAIL_TO}'
# On crée le dossier de téléchargement
os.makedirs(__DATA_DIR, exist_ok=True)
@@ -137,8 +222,12 @@ module = importlib.import_module(f'RAAspotter_{args.pref}')
raa_spotter = getattr(module, f'RAAspotter_{args.pref}')(__DATA_DIR)
raa_spotter.not_before = __NOT_BEFORE
-raa_spotter.configure_mailer(__SMTP_HOSTNAME, __SMTP_USERNAME, __SMTP_PASSWORD, __SMTP_PORT,
- __SMTP_STARTTLS, __SMTP_SSL, __EMAIL_FROM, __EMAIL_TO,
- f'[RAAspotter] [{raa_spotter.full_name}] Nouveaux éléments trouvés')
-raa_spotter.configure_mastodon(__MASTODON_ACCESS_TOKEN, __MASTODON_INSTANCE, f'[{raa_spotter.full_name}]', f'#{raa_spotter.short_code}')
+raa_spotter.configure_mailer(__SMTP_HOSTNAME, __SMTP_USERNAME, __SMTP_PASSWORD,
+ __SMTP_PORT, __SMTP_STARTTLS, __SMTP_SSL,
+ __EMAIL_FROM, __EMAIL_TO,
+ f'[RAAspotter] [{raa_spotter.full_name}] '
+ 'Nouveaux éléments trouvés')
+raa_spotter.configure_mastodon(__MASTODON_ACCESS_TOKEN, __MASTODON_INSTANCE,
+ f'[{raa_spotter.full_name}]',
+ f'#{raa_spotter.short_code}')
raa_spotter.get_raa(__KEYWORDS)