diff --git a/Attrap.py b/Attrap.py
index e02670f6756bc803b9f205b6c1731fab034d4792..7977e5dbf4182c8755f8d7d0677a79a9d36d6449 100644
--- a/Attrap.py
+++ b/Attrap.py
@@ -140,7 +140,7 @@ class Attrap:
self.tor_enabled = False
self.tor_max_requests = 0
self.tor_requests = 0
- self.not_before = datetime.datetime(2024, 1, 1)
+ self.not_before = datetime.datetime(2015, 1, 1)
self.smtp_configured = False
self.mastodon = None
self.mastodon_prefix = ''
@@ -405,7 +405,7 @@ class Attrap:
except requests.exceptions.ConnectionError:
logger.warning(f'Erreur de connexion, temporisation...')
self.tor_get_new_id()
- time.sleep(55)
+ time.sleep(60)
return self.get_page(url, method, data)
except requests.exceptions.Timeout:
logger.warning(f'Timeout, on relance la requête...')
diff --git a/Attrap_pref12.py b/Attrap_pref12.py
new file mode 100644
index 0000000000000000000000000000000000000000..4d4d48fd82ebc03ef092faef1526eac8a95ebee0
--- /dev/null
+++ b/Attrap_pref12.py
@@ -0,0 +1,138 @@
+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+import re
+from Attrap import Attrap
+
+
+class Attrap_pref46(Attrap):
+
+ # Config
+ __HOST = 'https://www.aveyron.gouv.fr'
+ __RAA_PAGE = f'{__HOST}/Publications/Recueil-des-actes-administratifs'
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+ full_name = "Préfecture de l'Aveyron"
+ short_code = 'pref12'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+ self.not_before = datetime.datetime(2020, 1, 1)# avant 2020 page "archives"
+ #supercharge pour classes css avec whitespaces
+ def get_sub_pages_with_pager(self, page, sub_page_element, pager_element, details_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)
+ sub_pages_details = None
+ if details_element is not None:
+ sub_pages_details = soup.select(details_element)
+ i = 0
+ for sub_page in sub_pages:
+ print(sub_page)
+ if sub_page.get('href'):
+ page = {
+ 'url': f"{host}{sub_page['href']}",
+ 'name': sub_page.get_text().strip(),
+ 'details': ''
+ }
+ if details_element is not None:
+ page['details'] = sub_pages_details[i].get_text().strip()
+ pages.append(page)
+ i = i + 1
+
+ # On recherche un pager, et si on le trouve on le suit
+ # modif ici, le parametre pager_element ne doit contenir
+ # que le contenu de la classe
+ # et pas l'element pour les classes avec whitespaces
+ pager = soup.find_all("a",class_=pager_element)
+ print(pager)
+ if pager and len(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,
+ details_element,
+ host
+ ):
+ pages.append(sub_page)
+
+ return pages
+
+ def get_raa(self, keywords):
+ elements = []
+ page_content = self.get_page(self.__RAA_PAGE, 'get').content
+ soup = BeautifulSoup(page_content, 'html.parser')
+ #selection des grey cards
+ for a in soup.select('div.fr-card--grey div.fr-card__body div.fr-card__content h2.fr-card__title a'):
+ #regular
+ if Attrap.guess_date(f'{a.get_text().strip()}', '([0-9]{4}).*').year >= self.not_before.year and "Archives" not in f'{a.get_text().strip()}':
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", 'get').content
+ for sub_page in self.get_sub_pages_with_pager(f"{self.__HOST}{a['href']}", 'div.fr-card__body div.fr-card__content h2.fr-card__title a', 'fr-pagination__link fr-pagination__link--next fr-pagination__link--lg-label', None, self.__HOST):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+ #archives
+ elif self.not_before.year<2021 and "Archives" in f'{a.get_text().strip()}':
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", '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,
+ True):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for a in sub_page_content.select('div.fr-card__body div.fr-card__content h2.fr-card__title a'):
+ sub_sub_page_content = self.get_page(a['url'], 'get').content
+ for element in self.get_raa_elements(sub_sub_page_content):
+ elements.append(element)
+ #selection des "spécials"
+ for div in soup.select("div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w"):
+ for a in div.select("div.fr-card__body div.fr-card__content h2.fr-card__title a"):
+ print(a)
+ search_pattern=re.search('(?<=Publié le).*',f'{a.parent.parent.get_text()}')
+ if search_pattern:
+ if Attrap.guess_date(search_pattern[0], '([0-9]{4}).*').year>=self.not_before.year:
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", '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,
+ True):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+ #bug sur ocrmypdf sur mon ubuntu 20.04 (test avec arch prochainement)
+ #sur --invalidate-digital-signatures bien que dans la doc
+ #ici https://ocrmypdf.readthedocs.io/en/latest/pdfsecurity.html
+ self.parse_raa(elements, keywords)
+ 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
+ print(soup.find_all("a",{"id":'class="fr-link'}))
+ print(len(soup.find_all("a",{"id":'class="fr-link'})))
+ for a in soup.find_all("a",{"id":'class="fr-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.find('span').previous_sibling.replace('Télécharger ', '').strip()
+ date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
+ raa = Attrap.RAA(url, date, name)
+ self.download_file(raa)
+ elements.append(raa)
+ print(elements)
+ return elements
+
diff --git a/Attrap_pref40.py b/Attrap_pref40.py
new file mode 100644
index 0000000000000000000000000000000000000000..51f882be9672aaa11747f79bcb5984ae06071b91
--- /dev/null
+++ b/Attrap_pref40.py
@@ -0,0 +1,120 @@
+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+
+class Attrap_pref40(Attrap):
+
+ # Config
+ __HOST = 'https://www.landes.gouv.fr'
+ __RAA_PAGE = f'{__HOST}/Publications/Publications-legales/Le-Recueil-des-Actes-Administratifs-RAA'
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture des Landes'
+ short_code = 'pref40'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+ self.not_before = datetime.datetime(2016, 1, 1)# avant 2016 page "années antérieures"
+ #supercharge pour classes css avec whitespaces
+ def get_sub_pages_with_pager(self, page, sub_page_element, pager_element, details_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)
+ sub_pages_details = None
+ if details_element is not None:
+ sub_pages_details = soup.select(details_element)
+ i = 0
+ for sub_page in sub_pages:
+ print(sub_page)
+ if sub_page.get('href'):
+ page = {
+ 'url': f"{host}{sub_page['href']}",
+ 'name': sub_page.get_text().strip(),
+ 'details': ''
+ }
+ if details_element is not None:
+ page['details'] = sub_pages_details[i].get_text().strip()
+ pages.append(page)
+ i = i + 1
+
+ # On recherche un pager, et si on le trouve on le suit
+ # modif ici, le parametre pager_element ne doit contenir
+ # que le contenu de la classe
+ # et pas l'element pour les classes avec whitespaces
+ pager = soup.find_all("a",class_=pager_element)
+ print(pager)
+ if pager and len(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,
+ details_element,
+ host
+ ):
+ pages.append(sub_page)
+
+ return pages
+
+ def get_raa(self, keywords):
+ elements = []
+ page_content = self.get_page(self.__RAA_PAGE, 'get').content
+ soup = BeautifulSoup(page_content, 'html.parser')
+ for a in soup.select('div.fr-card__body div.fr-card__content h2.fr-card__title a'):
+ # Annee archivees
+ if self.not_before.year<2016 and "antérieures" in a.get_text().strip():
+ print(f"{a.get_text().strip()}")
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", 'get').content
+ for sub_page in self.get_sub_pages_with_pager(f"{self.__HOST}{a['href']}", 'div.fr-card__body div.fr-card__content h2.fr-card__title a', 'fr-pagination__link fr-pagination__link--next fr-pagination__link--lg-label', None, self.__HOST):
+ if Attrap.guess_date(f'{sub_page.get_text().strip()}', '([0-9]{4}).*').year>=self.not_before.year:
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+ # Annees non archivees
+ elif Attrap.guess_date(f'{a.get_text().strip()}', '([0-9]{4}).*').year >= self.not_before.year and "antérieures" not in a.get_text().strip():
+ print(f"{a.get_text().strip()}")
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", 'get').content
+ for sub_page in self.get_sub_pages_with_pager(f"{self.__HOST}{a['href']}", 'div.fr-card__body div.fr-card__content h2.fr-card__title a', 'fr-pagination__link fr-pagination__link--next fr-pagination__link--lg-label', None, self.__HOST):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+
+ #bug sur ocrmypdf sur mon ubuntu 20.04 (test avec arch prochainement)
+ #sur --invalidate-digital-signatures bien que dans la doc
+ #ici https://ocrmypdf.readthedocs.io/en/latest/pdfsecurity.html
+ self.parse_raa(elements, keywords)
+ 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",{"id":'class="fr-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.find('span').previous_sibling.replace('Télécharger ', '').strip()
+ date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
+ raa = Attrap.RAA(url, date, name)
+ self.download_file(raa)
+ elements.append(raa)
+ print(elements)
+ return elements
+
+
diff --git a/Attrap_pref46.py b/Attrap_pref46.py
new file mode 100644
index 0000000000000000000000000000000000000000..56b215e85168f52aeaabae48294936f865e5b1e8
--- /dev/null
+++ b/Attrap_pref46.py
@@ -0,0 +1,136 @@
+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+import re
+from Attrap import Attrap
+
+
+class Attrap_pref46(Attrap):
+
+ # Config
+ __HOST = 'https://www.lot.gouv.fr'
+ __RAA_PAGE = f'{__HOST}/Publications/Recueil-des-Actes-Administratifs'
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture du Lot'
+ short_code = 'pref46'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+ self.not_before = datetime.datetime(2020, 1, 1)# avant 2020 page "archives"
+ #supercharge pour classes css avec whitespaces
+ def get_sub_pages_with_pager(self, page, sub_page_element, pager_element, details_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)
+ sub_pages_details = None
+ if details_element is not None:
+ sub_pages_details = soup.select(details_element)
+ i = 0
+ for sub_page in sub_pages:
+ print(sub_page)
+ if sub_page.get('href'):
+ page = {
+ 'url': f"{host}{sub_page['href']}",
+ 'name': sub_page.get_text().strip(),
+ 'details': ''
+ }
+ if details_element is not None:
+ page['details'] = sub_pages_details[i].get_text().strip()
+ pages.append(page)
+ i = i + 1
+
+ # On recherche un pager, et si on le trouve on le suit
+ # modif ici, le parametre pager_element ne doit contenir
+ # que le contenu de la classe
+ # et pas l'element pour les classes avec whitespaces
+ pager = soup.find_all("a",class_=pager_element)
+ print(pager)
+ if pager and len(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,
+ details_element,
+ host
+ ):
+ pages.append(sub_page)
+
+ return pages
+
+ def get_raa(self, keywords):
+ elements = []
+ page_content = self.get_page(self.__RAA_PAGE, 'get').content
+ soup = BeautifulSoup(page_content, 'html.parser')
+ #selection des grey cards
+ for a in soup.select('div.fr-card--grey div.fr-card__body div.fr-card__content h2.fr-card__title a'):
+ #regular
+ if Attrap.guess_date(f'{a.get_text().strip()}', '([0-9]{4}).*').year >= self.not_before.year and "Archives" not in f'{a.get_text().strip()}':
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", 'get').content
+ for sub_page in self.get_sub_pages_with_pager(f"{self.__HOST}{a['href']}", 'div.fr-card__body div.fr-card__content h2.fr-card__title a', 'fr-pagination__link fr-pagination__link--next fr-pagination__link--lg-label', None, self.__HOST):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+ #archives
+ elif self.not_before.year<2020 and "Archives" in f'{a.get_text().strip()}':
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", '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,
+ True):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+ #selection des "spécials"
+ for div in soup.select("div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w"):
+ for a in div.select("div.fr-card__body div.fr-card__content h2.fr-card__title a"):
+ print(a)
+ search_pattern=re.search('(?<=Publié le).*',f'{a.parent.parent.get_text()}')
+ if search_pattern:
+ if Attrap.guess_date(search_pattern[0], '([0-9]{4}).*').year>=self.not_before.year:
+ page_content = self.get_page(f"{self.__HOST}{a['href']}", '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,
+ True):
+ sub_page_content = self.get_page(sub_page['url'], 'get').content
+ for element in self.get_raa_elements(sub_page_content):
+ elements.append(element)
+ #bug sur ocrmypdf sur mon ubuntu 20.04 (test avec arch prochainement)
+ #sur --invalidate-digital-signatures bien que dans la doc
+ #ici https://ocrmypdf.readthedocs.io/en/latest/pdfsecurity.html
+ self.parse_raa(elements, keywords)
+ 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
+ print(soup.find_all("a",{"id":'class="fr-link'}))
+ print(len(soup.find_all("a",{"id":'class="fr-link'})))
+ for a in soup.find_all("a",{"id":'class="fr-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.find('span').previous_sibling.replace('Télécharger ', '').strip()
+ date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
+ raa = Attrap.RAA(url, date, name)
+ self.download_file(raa)
+ elements.append(raa)
+ print(elements)
+ return elements
+
diff --git a/Attrap_pref47.py b/Attrap_pref47.py
index 8f9110e8a7bde33a2f6418cd1af301879c288d76..c066f3bf5732317570c9148dcac8d8cd31ded2b5 100644
--- a/Attrap_pref47.py
+++ b/Attrap_pref47.py
@@ -85,7 +85,7 @@ class Attrap_pref47(Attrap):
#les raa de 2019 et années précédentes ont des pagers
#else:
# page_content = self.get_page(f"{self.__HOST}{a['href']}", 'get').content
- # for sub_page in self.get_sub_pages_with_pager(f"{self.__HOST}{a['href']}", 'div.fr-card__body div.fr-card__content h2.fr-card__title a', 'a.fr-pagination__link fr-pagination__link--next fr-pagination__link--lg-label', None, self.__HOST):
+ # for sub_page in self.get_sub_pages_with_pager(f"{self.__HOST}{a['href']}", 'div.fr-card__body div.fr-card__content h2.fr-card__title a', 'fr-pagination__link fr-pagination__link--next fr-pagination__link--lg-label', None, self.__HOST):
# sub_page_content = self.get_page(sub_page['url'], 'get').content
# for element in self.get_raa_elements(sub_page_content):
# elements.append(element)
diff --git a/Makefile b/Makefile
index 54f6736301319dea091e8ff43aa1251a066f523c..e05a47a017ec13a6d11de079d1321dc995bb4a16 100644
--- a/Makefile
+++ b/Makefile
@@ -9,6 +9,8 @@ pref06:
bin/python3 cli.py pref06
pref09:
bin/python3 cli.py pref09
+pref12:
+ bin/python3 cli.py pref12
pref13:
bin/python3 cli.py pref13
pref31:
@@ -21,10 +23,14 @@ pref35:
bin/python3 cli.py pref35
pref38:
bin/python3 cli.py pref38
+pref40:
+ bin/python3 cli.py pref40
pref42:
bin/python3 cli.py pref42
pref44:
bin/python3 cli.py pref44
+pref46:
+ bin/python3 cli.py pref46
pref47:
bin/python3 cli.py pref47
pref59:
diff --git a/cli.py b/cli.py
index a427fb0f20a8c692ecf69857a357b98e9efeb37d..da8ed5d0da819bcf48501a16fd45e70215f08898 100755
--- a/cli.py
+++ b/cli.py
@@ -42,14 +42,17 @@ available_administrations = [
'pref05',
'pref06',
'pref09',
+ 'pref12',
'pref13',
'pref31',
'pref33',
'pref34',
'pref35',
'pref38',
+ 'pref40',
'pref42',
'pref44',
+ 'pref46',
'pref47',
'pref59',
'pref62',