Skip to content
Extraits de code Groupes Projets

Comparer les révisions

Les modifications sont affichées comme si la révision source était fusionnée avec la révision cible. En savoir plus sur la comparaison des révisions.

Source

Sélectionner le projet cible
No results found

Cible

Sélectionner le projet cible
  • la-quadrature-du-net/Attrap
  • foggyfrog/Attrap
  • skhwiz/Attrap
  • precambrien/Attrap
  • ketsapiwiq/Attrap
  • Joseki/Attrap
  • kr1p/attrap-pref-12
  • kr1p/attrap-pref-46
  • kr1p/attrap-pi
  • Guinness/Attrap
  • astroidgritty/attrap-pref-84
  • davinov/Attrap
  • maettellite/attrap-pref-01
  • m242/Attrap
  • multi/Attrap
  • mverdeil/Attrap
  • olpo/Attrap
17 résultats
Afficher les modifications
Validations sur la source (129)
29 additional commits have been omitted to prevent performance issues.
Tout étendre Masquer les modifications d'espaces
En ligne Côte à côte
Affichage de
avec 403 ajouts et 777 suppressions
.gitignore
Voir le fichier @ f1d8eaac
......@@ -6,3 +6,4 @@ data/
pyvenv.cfg
output_*.log
*.patch
CACHEDIR.TAG
.gitlab-ci.yml
Voir le fichier @ f1d8eaac
......@@ -74,11 +74,11 @@ pep8:
- unprivileged
needs: [install]
script:
- s3/download-from-s3.sh "${PREF}" "${S3_KEY}" "${S3_SECRET}" "${S3_HOST}" "${S3_BUCKET}" data/ || true
- misc/download-from-s3.sh "${PREF}" "${S3_KEY}" "${S3_SECRET}" "${S3_HOST}" "${S3_BUCKET}" data/ || true
- source bin/activate
- /etc/init.d/tor start
- make "${PREF}"
- s3/upload-to-s3.sh "${PREF}" "${S3_KEY}" "${S3_SECRET}" "${S3_HOST}" "${S3_BUCKET}" data/ || true
- misc/upload-to-s3.sh "${PREF}" "${S3_KEY}" "${S3_SECRET}" "${S3_HOST}" "${S3_BUCKET}" data/ || true
cache:
key: $CI_COMMIT_REF_SLUG
paths:
......@@ -99,9 +99,14 @@ test_ppparis:
PREF: "ppparis"
extends: .default_pref
test_pref2b:
test_pref01:
variables:
PREF: "pref2b"
PREF: "pref01"
extends: .default_pref
test_pref02:
variables:
PREF: "pref02"
extends: .default_pref
test_pref03:
......@@ -134,16 +139,41 @@ test_pref10:
PREF: "pref10"
extends: .default_pref
test_pref11:
variables:
PREF: "pref11"
extends: .default_pref
test_pref13:
variables:
PREF: "pref13"
extends: .default_pref
test_pref2a:
variables:
PREF: "pref2a"
extends: .default_pref
test_pref2b:
variables:
PREF: "pref2b"
extends: .default_pref
test_pref25:
variables:
PREF: "pref25"
extends: .default_pref
test_pref29:
variables:
PREF: "pref29"
extends: .default_pref
test_pref30:
variables:
PREF: "pref30"
extends: .default_pref
test_pref31:
variables:
PREF: "pref31"
......@@ -169,6 +199,11 @@ test_pref38:
PREF: "pref38"
extends: .default_pref
test_pref39:
variables:
PREF: "pref39"
extends: .default_pref
test_pref42:
variables:
PREF: "pref42"
......@@ -179,11 +214,41 @@ test_pref44:
PREF: "pref44"
extends: .default_pref
test_pref49:
variables:
PREF: "pref49"
extends: .default_pref
test_pref50:
variables:
PREF: "pref50"
extends: .default_pref
test_pref52:
variables:
PREF: "pref52"
extends: .default_pref
test_pref54:
variables:
PREF: "pref54"
extends: .default_pref
test_pref55:
variables:
PREF: "pref55"
extends: .default_pref
test_pref59:
variables:
PREF: "pref59"
extends: .default_pref
test_pref61:
variables:
PREF: "pref61"
extends: .default_pref
test_pref62:
variables:
PREF: "pref62"
......@@ -224,6 +289,16 @@ test_pref75:
PREF: "pref75"
extends: .default_pref
test_pref76:
variables:
PREF: "pref76"
extends: .default_pref
test_pref77:
variables:
PREF: "pref77"
extends: .default_pref
test_pref80:
variables:
PREF: "pref80"
......@@ -244,6 +319,16 @@ test_pref87:
PREF: "pref87"
extends: .default_pref
test_pref91:
variables:
PREF: "pref91"
extends: .default_pref
test_pref92:
variables:
PREF: "pref92"
extends: .default_pref
test_pref93:
variables:
PREF: "pref93"
......@@ -259,7 +344,17 @@ test_pref976:
PREF: "pref976"
extends: .default_pref
test_prefIdf:
test_prefbretagne:
variables:
PREF: "prefbretagne"
extends: .default_pref
test_prefidf:
variables:
PREF: "prefidf"
extends: .default_pref
test_prefpaca:
variables:
PREF: "prefIdf"
PREF: "prefpaca"
extends: .default_pref
Attrap.py
Voir le fichier @ f1d8eaac
Ce diff est replié.
Attrap_ppparis.py
Voir le fichier @ f1d8eaac
......@@ -9,18 +9,19 @@ from Attrap import Attrap
class Attrap_ppparis(Attrap):
# Config
__HOST = 'https://www.prefecturedepolice.interieur.gouv.fr'
__RAA_PAGE = f'{__HOST}/actualites-et-presse/arretes/accueil-arretes'
hostname = 'https://www.prefecturedepolice.interieur.gouv.fr'
raa_page = f'{hostname}/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'
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'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
super().__init__(data_dir, self.user_agent)
def get_raa(self, keywords):
page_content = self.get_session(self.__RAA_PAGE, self.__WAIT_ELEMENT, 6)
page_content = self.get_session(self.raa_page, self.__WAIT_ELEMENT, 6)
raa_elements = self.get_raa_elements(page_content)
self.parse_raa(raa_elements, keywords)
self.mailer()
......@@ -43,6 +44,6 @@ class Attrap_ppparis(Attrap):
name = a.find('span').get_text()
date = datetime.datetime.strptime(a.find('div', class_="field--type-datetime").get_text().strip(), '%d/%m/%Y')
raa = Attrap.RAA(url, date, name)
raa = Attrap.RAA(url, date, name, timezone=self.timezone)
elements.append(raa)
return elements
Attrap_pref01.py 0 → 100644
Voir le fichier @ f1d8eaac
from Attrap_prefdpt import Attrap_prefdpt
class Attrap_pref01(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.ain.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-RAA'
full_name = 'Préfecture de l\'Ain'
short_code = 'pref01'
timezone = 'Europe/Paris'
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = '(?:Recueil|Recueils) (?:des actes administratifs)(?:[ -])*([0-9]{4})'
Attrap_pref02.py 0 → 100644
Voir le fichier @ f1d8eaac
from Attrap_prefdpt import Attrap_prefdpt
class Attrap_pref02(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.aisne.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs'
full_name = 'Préfecture de l\'Aisne'
short_code = 'pref02'
timezone = 'Europe/Paris'
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'RAA [Aa]nnée ([0-9]{4})'
Attrap_pref03.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref03(Attrap_prefdpt):
class Attrap_pref03(Attrap):
# Config
__HOST = 'https://www.allier.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Recueil-des-actes-administratifs-arretes'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:129.0) Gecko/20100101 Firefox/129.0'
# Configuration de la préfecture
hostname = 'https://www.allier.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-arretes'
full_name = 'Préfecture de l\'Allier'
short_code = 'pref03'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
elements = []
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 Attrap.guess_date(sub_page['name'], '.* ([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)
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.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')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'
Attrap_pref04.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref04(Attrap_prefdpt):
class Attrap_pref04(Attrap):
# 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'
# Configuration de la préfecture
hostname = 'https://www.alpes-de-haute-provence.gouv.fr'
raa_page = f'{hostname}/Publications/Publications-administratives-et-legales/Recueil-des-Actes-Administratifs'
full_name = 'Préfecture des Alpes-de-Haute-Provence'
short_code = 'pref04'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
elements = []
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 Attrap.guess_date(sub_page['name'], '([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)
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.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')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'
Attrap_pref05.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref05(Attrap_prefdpt):
class Attrap_pref05(Attrap):
# Config
__HOST = 'https://www.hautes-alpes.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'
# Configuration de la préfecture
hostname = 'https://www.hautes-alpes.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
full_name = 'Préfecture des Hautes-Alpes'
short_code = 'pref05'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
year_pages_to_parse = []
# On détermine quelles pages d'année parser
page_content = self.get_page(self.__RAA_PAGE, 'get').content
year_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
)
for year_page in year_pages:
if int(year_page['name'].replace('Année ', '').strip()) >= self.not_before.year:
year_pages_to_parse.append(year_page['url'])
month_pages_to_parse = []
# Pour chaque année, on cherche les sous-pages de mois
for year_page in year_pages_to_parse:
page_content = self.get_page(year_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:
# On filtre les mois ne correspondant pas à la période analysée
guessed_date = Attrap.guess_date(month_page['name'], '(.*)')
if guessed_date.replace(day=1) >= self.not_before.replace(day=1):
month_pages_to_parse.append(month_page['url'])
pages_to_parse = []
# Pour chaque page de mois, on cherche les pages de RAA
for month_page in month_pages_to_parse:
pages = self.get_sub_pages_with_pager(
month_page,
'div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link',
'nav.fr-pagination ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next.fr-pagination__link--lg-label',
'div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w div.fr-card__body div.fr-card__content div.fr-card__end p.fr-card__detail',
self.__HOST
)[::-1]
for page in pages:
guessed_date = datetime.datetime.strptime(page['details'].replace('Publié le ', '').strip(), '%d/%m/%Y')
if guessed_date.replace(day=1) >= self.not_before.replace(day=1):
pages_to_parse.append(page['url'])
elements = []
# On parse les pages contenant des RAA
for page in pages_to_parse:
page_content = self.get_page(page, 'get').content
for element in self.get_raa_elements(page_content):
elements.append(element)
# On parse les RAA
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')
# On récupère chaque balise a
for a in soup.select('div.fr-grid-row div.fr-downloads-group.fr-downloads-group--bordered ul li a'):
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)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'Année *([0-9]{4})'
Attrap_prefdpt.grey_card['regex']['month'] = '([A-Za-zéû]* *[0-9]{4})'
Attrap_pref06.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref06(Attrap_prefdpt):
class Attrap_pref06(Attrap):
# 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'
# Configuration de la préfecture
hostname = 'https://www.alpes-maritimes.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-RAA'
full_name = 'Préfecture des Alpes-Maritimes'
short_code = 'pref06'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
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)
self.mailer()
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']
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')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'Année *([0-9]{4})'
Attrap_pref09.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref09(Attrap_prefdpt):
class Attrap_pref09(Attrap):
# Config
__HOST = 'https://www.ariege.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-l-Ariege-a-partir-du-28-avril-2015'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
# Configuration de la préfecture
hostname = 'https://www.ariege.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-l-Ariege-a-partir-du-28-avril-2015'
full_name = 'Préfecture de l\'Ariège'
short_code = 'pref09'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
pages_to_parse = []
# Les RAA de l'Ariège sont éparpillés sur des sous-pages par mois.
# Donc on parse la page principale à la recherche des sous-pages.
sub_pages = self.get_sub_pages_with_pager(
self.__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.fr-pagination__link--next',
'div.fr-card__body div.fr-card__content div.fr-card__end p.fr-card__detail',
self.__HOST
)[::-1]
# On filtre par date les sous-pages pour limiter les requêtes
for sub_page in sub_pages:
guessed_date = datetime.datetime.strptime(sub_page['details'].replace('Publié le ', '').strip(), '%d/%m/%Y')
guessed_date.replace(day=1)
if guessed_date >= self.not_before:
pages_to_parse.append(sub_page['url'])
# On parse les pages contenant des RAA
elements = []
for page in pages_to_parse:
page_content = self.get_page(page, 'get').content
for element in self.get_raa_elements(page_content):
elements.append(element)
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')
# On récupère chaque balise a
for a in soup.select('div.fr-downloads-group.fr-downloads-group--bordered ul li a'):
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)
elements.append(raa)
return elements
timezone = 'Europe/Paris'
Attrap_pref10.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref10(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.aube.gouv.fr'
raa_page = [
f'{hostname}/Publications/RAA-Recueil-des-Actes-Administratifs',
f'{hostname}/Publications/RAA-Recueil-des-Actes-Administratifs/RAA-Archives'
]
class Attrap_pref10(Attrap):
# Config
__HOST = 'https://www.aube.gouv.fr'
__RAA_ARCHIVES_PAGE = f'{__HOST}/Publications/RAA-Recueil-des-Actes-Administratifs/RAA-Archives/'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:129.0) Gecko/20100101 Firefox/129.0'
full_name = 'Préfecture de l\'Aube'
short_code = 'pref10'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
# La préfecture de l'Aube a une page avec ses archives, et une page avec l'année en cours. On parse
# donc le menu déroulant de la gauche de la page d'archives (et non le contenu de la page) pour récupérér,
# premièrement, la page d'année en cours et, deuxièmement, les années archivées.
pages_to_parse = []
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'RAA *([0-9]{4})'
archives_page_content = self.get_page(self.__RAA_ARCHIVES_PAGE, 'get').content
for year_page in self.get_sub_pages(
archives_page_content,
'ul.fr-sidemenu__list a.fr-sidemenu__link',
self.__HOST,
False,
):
if Attrap.guess_date(year_page['name'], '.* ([0-9]{4})').year >= self.not_before.year:
pages_to_parse.append(year_page['url'])
elements = self.get_raa_with_pager(
pages_to_parse,
'ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next',
self.__HOST
# On ajoute un widget custom représentant les liens sur la page d'accueil
Attrap_prefdpt.widgets.append(
Attrap_prefdpt.DptWidget(
'homepage_links',
regex={'year': 'Année *([0-9]{4})'},
css_path={'title': 'div.fr-text--lead p a.fr-link'}
)
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')
# On récupère chaque balise a
for a in soup.select('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.text.strip()
date = datetime.datetime.strptime(a['title'].split(' - ')[-1].strip(), '%d/%m/%Y')
if date >= self.not_before:
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
)
Attrap_pref11.py 0 → 100644
Voir le fichier @ f1d8eaac
from Attrap_prefdpt import Attrap_prefdpt
class Attrap_pref11(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.aude.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs-RAA'
full_name = 'Préfecture de l\'Aude'
short_code = 'pref11'
timezone = 'Europe/Paris'
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'Année *([0-9]{4})'
Attrap_pref13.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref13(Attrap_prefdpt):
class Attrap_pref13(Attrap):
# 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'
# Configuration de la préfecture
hostname = 'https://www.bouches-du-rhone.gouv.fr'
raa_page = [
f'{hostname}/Publications/RAA-et-Archives',
f'{hostname}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone'
]
__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'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
elements = []
for raa_page in self.__RAA_PAGE:
page_content = self.get_page(raa_page, 'get').content
for element in self.get_raa_elements(page_content):
elements.append(element)
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.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')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'RAA[- ]*([0-9]{4})'
Attrap_prefdpt.grey_card['follow_link_on_unrecognised_date'] = False
Attrap_pref25.py
Voir le fichier @ f1d8eaac
import os
import datetime
import logging
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
logger = logging.getLogger(__name__)
class Attrap_pref25(Attrap):
# Config
__HOST = 'https://www.doubs.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Publications-Legales/Recueil-des-Actes-Administratifs-RAA'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
class Attrap_pref25(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.doubs.gouv.fr'
raa_page = f'{hostname}/Publications/Publications-Legales/Recueil-des-Actes-Administratifs-RAA'
full_name = 'Préfecture du Doubs'
short_code = 'pref25'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
sub_pages = self.get_sub_pages_with_pager(
self.__RAA_PAGE,
'a.fr-card__link',
'a.fr-pagination__link.fr-pagination__link--next.fr-pagination__link--lg-label',
None,
self.__HOST,
)
pages_to_parse = []
# TODO : détecter la date de la page à partir du parsing de la page principale et non à partir de son URL
for sub_page in sub_pages:
url = sub_page['url']
last_word = url.split('-')[-1]
year = 0
try:
year = int(last_word)
if self.not_before.year <= year:
pages_to_parse.append(url)
except Exception as e:
logger.warning(f"Impossible de déterminer l'année de l'URL {url}")
elements = []
for raa_page in pages_to_parse:
page_content = self.get_page(raa_page, 'get').content
elements.extend(self.get_raa_elements(page_content))
self.parse_raa(elements[::-1], keywords)
self.mailer()
def get_raa_elements(self, page_content):
# On charge le parser
soup = BeautifulSoup(page_content, 'html.parser')
elements = []
# On récupère chaque balise a
for a in soup.select('div.fr-downloads-group.fr-downloads-group--bordered ul li a'):
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').text.split(' - ')[-1].strip(), '%d/%m/%Y')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'
Attrap_prefdpt.grey_card['follow_link_on_unrecognised_date'] = False
Attrap_pref29.py 0 → 100644
Voir le fichier @ f1d8eaac
from Attrap_prefdpt import Attrap_prefdpt
class Attrap_pref29(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.finistere.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
full_name = 'Préfecture du Finistère'
short_code = 'pref29'
timezone = 'Europe/Paris'
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = '(?:Recueils publiés en ).*([0-9]{4})'
Attrap_pref2a.py 0 → 100644
Voir le fichier @ f1d8eaac
from Attrap_prefdpt import Attrap_prefdpt
class Attrap_pref2a(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.corse-du-sud.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs/Recueil-des-actes-administratifs-de-la-prefecture-de-la-Corse-du-Sud'
full_name = 'Préfecture de la Corse-du-Sud'
short_code = 'pref2a'
timezone = 'Europe/Paris'
# Configuration des widgets à analyser
Attrap_prefdpt.white_card['regex']['year'] = '([0-9]{4})'
Attrap_pref2b.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref2b(Attrap_prefdpt):
class Attrap_pref2b(Attrap):
# Config
__HOST = 'https://www.haute-corse.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Publications-administratives-et-legales/Recueils-des-actes-administratifs'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:129.0) Gecko/20100101 Firefox/129.0'
# Configuration de la préfecture
hostname = 'https://www.haute-corse.gouv.fr'
raa_page = f'{hostname}/Publications/Publications-administratives-et-legales/Recueils-des-actes-administratifs'
full_name = 'Préfecture de Haute-Corse'
short_code = 'pref2b'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
# La préfecture de Haute-Corse organise son site avec une page dédiée à l'année N, une autre dédiée à l'année N-1,
# puis les années d'avant sont regroupées ensemble sur deux pages. On doit donc parser les pages jusqu'à ce qu'on ne
# tombe plus sur des cartes d'années.
pages_to_parse = []
page_content = self.get_page(self.__RAA_PAGE, 'get').content
for card in self.get_sub_pages(
page_content,
'div.fr-card__body div.fr-card__content h2.fr-card__title a',
self.__HOST,
False
):
if Attrap.guess_date(card['name'], '[a-z]* ([0-9]{4})').year >= self.not_before.year:
pages_to_parse.append(card['url'])
else:
# Si on n'a pas trouvé une page d'année, on tente de parser la page à la rechercge
# de sous-pages (et sinon on ignore la page)
page_content = self.get_page(card['url'], 'get').content
for card in self.get_sub_pages(
page_content,
'div.fr-card__body div.fr-card__content h2.fr-card__title a',
self.__HOST,
False
):
if Attrap.guess_date(card['name'], '[a-z]* ([0-9]{4})').year >= self.not_before.year:
pages_to_parse.append(card['url'])
# Pour chaque année, on cherche les sous-pages de mois
month_pages_to_parse = []
for year_page in pages_to_parse:
for month_page in self.get_sub_pages_with_pager(
year_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',
None,
self.__HOST
):
if Attrap.guess_date(month_page['name'], '([a-zûé]* [0-9]{4})').replace(day=1) >= self.not_before.replace(day=1):
month_pages_to_parse.append(month_page['url'])
# On parse les pages contenant des RAA
elements = []
for page in month_pages_to_parse:
page_content = self.get_page(page, 'get').content
for element in self.get_raa_elements(page_content):
elements.append(element)
self.parse_raa(elements[::-1], keywords)
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('div.fr-downloads-group.fr-downloads-group--bordered ul li a'):
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)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = 'Recueils des actes administratifs ([0-9]{4})'
Attrap_prefdpt.white_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'
Attrap_pref30.py 0 → 100644
Voir le fichier @ f1d8eaac
from Attrap_prefdpt import Attrap_prefdpt
class Attrap_pref30(Attrap_prefdpt):
# Configuration de la préfecture
hostname = 'https://www.gard.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs'
full_name = 'Préfecture du Gard'
short_code = 'pref30'
timezone = 'Europe/Paris'
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'
Attrap_pref31.py
Voir le fichier @ f1d8eaac
import os
import datetime
from Attrap_prefdpt import Attrap_prefdpt
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref31(Attrap_prefdpt):
class Attrap_pref31(Attrap):
# Config
__HOST = 'https://www.haute-garonne.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Recueil-des-Actes-Administratifs/Recueil-des-Actes-Administratifs-Haute-Garonne'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
# Configuration de la préfecture
hostname = 'https://www.haute-garonne.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs/Recueil-des-Actes-Administratifs-Haute-Garonne'
full_name = 'Préfecture de la Haute-Garonne'
short_code = 'pref31'
timezone = 'Europe/Paris'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
def get_raa(self, keywords):
# On cherche les pages de chaque mois
page_content = self.get_page(self.__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]
pages_to_parse = []
# On filtre les pages de mois pour limiter le nombre de requêtes
for month_page in month_pages:
guessed_date = Attrap.guess_date(month_page['name'], '([a-zéû]* [0-9]{4})')
if guessed_date >= self.not_before.replace(day=1):
pages_to_parse.append(month_page['url'])
elements = []
# On parse les pages des mois qu'on veut analyser
for element in self.get_raa_with_pager(
pages_to_parse,
".fr-pagination__link.fr-pagination__link--next",
self.__HOST
):
elements.append(element)
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')
# On récupère chaque balise a
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().capitalize()
date = datetime.datetime.strptime(a['title'].split(' - ')[-1].strip(), '%d/%m/%Y')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements
# Configuration des widgets à analyser
Attrap_prefdpt.grey_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'