From 24ea416cb6a7e51a8e26e3b9550e8ad52cf082f1 Mon Sep 17 00:00:00 2001
From: Aurel <aurel.pere@ikmail.com>
Date: Fri, 7 Jun 2024 16:01:23 +0200
Subject: [PATCH] update cli.py,Makefile,comment old years pager crawling
---
Attrap_pref47.py | 123 +++++++++++++++++++++++++++++++++++++++++++++++
Makefile | 4 +-
cli.py | 1 +
3 files changed, 127 insertions(+), 1 deletion(-)
create mode 100644 Attrap_pref47.py
diff --git a/Attrap_pref47.py b/Attrap_pref47.py
new file mode 100644
index 0000000..209fec9
--- /dev/null
+++ b/Attrap_pref47.py
@@ -0,0 +1,123 @@
+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+
+class Attrap_pref47(Attrap):
+
+ # Config
+ __HOST = 'https://www.lot-et-garonne.gouv.fr'
+ __RAA_PAGE = f'{__HOST}/Publications/Publications-legales/RAA'
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture du Lot-et-garonne'
+ short_code = 'pref47'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(10)
+ self.not_before = datetime.datetime(2020, 1, 1) # annee de differenciation pager
+
+
+ #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'):
+ # Annees sans pager
+ if Attrap.guess_date(f'{self.__HOST}{a.get_text().strip()}', '([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)
+ #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):
+ # 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/Makefile b/Makefile
index dbbd7dd..54f6736 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-make: ppparis pref04 pref05 pref06 pref09 pref13 pref31 pref33 pref34 pref35 pref38 pref42 pref44 pref59 pref62 pref63 pref64 pref65 pref66 pref69 pref80 pref81 pref83 pref87 pref93 pref976
+make: ppparis pref04 pref05 pref06 pref09 pref13 pref31 pref33 pref34 pref35 pref38 pref42 pref44 pref47 pref59 pref62 pref63 pref64 pref65 pref66 pref69 pref80 pref81 pref83 pref87 pref93 pref976
ppparis:
bin/python3 cli.py ppparis
pref04:
@@ -25,6 +25,8 @@ pref42:
bin/python3 cli.py pref42
pref44:
bin/python3 cli.py pref44
+pref47:
+ bin/python3 cli.py pref47
pref59:
bin/python3 cli.py pref59
pref62:
diff --git a/cli.py b/cli.py
index 275bb16..8191d43 100755
--- a/cli.py
+++ b/cli.py
@@ -52,6 +52,7 @@ available_administrations = [
'pref38',
'pref42',
'pref44',
+ 'pref47',
'pref59',
'pref62',
'pref63',
--
GitLab