Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved Brand Eins

Browse Source
This commit is contained in:
Kovid Goyal 2010-11-21 08:27:48 -07:00
parent 1f720bec77
commit cf2a9008ed
1 changed files with 30 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
resources/recipes/brand_eins.recipe
View File

@ -1,18 +1,22 @@
#!/usr/bin/env python #!/usr/bin/env python
# -*- coding: utf-8 -*- # -*- coding: utf-8 mode: python -*-
# Find the newest version of this recipe here:
# https://github.com/consti/BrandEins-Recipe/raw/master/brandeins.recipe
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Constantin Hofstetter <consti at consti.de>' __copyright__ = '2010, Constantin Hofstetter <consti at consti.de>, Steffen Siebert <calibre at steffensiebert.de>'
__version__ = '0.95' __version__ = '0.96'
''' http://brandeins.de - Wirtschaftsmagazin ''' ''' http://brandeins.de - Wirtschaftsmagazin '''
import re import re
import string import string
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class BrandEins(BasicNewsRecipe): class BrandEins(BasicNewsRecipe):
title = u'Brand Eins' title = u'brand eins'
__author__ = 'Constantin Hofstetter' __author__ = 'Constantin Hofstetter'
description = u'Wirtschaftsmagazin' description = u'Wirtschaftsmagazin'
publisher ='brandeins.de' publisher ='brandeins.de'
@ -22,11 +26,14 @@ class BrandEins(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
language = 'de' language = 'de'
publication_type = 'magazine'
needs_subscription = True
# 2 is the last full magazine (default) # 2 is the last full magazine (default)
# 1 is the newest (but not full) # 1 is the newest (but not full)
# 3 is one before 2 etc. # 3 is one before 2 etc.
which_ausgabe = 2 # This value can be set via the username field.
default_issue = 2
keep_only_tags = [dict(name='div', attrs={'id':'theContent'}), dict(name='div', attrs={'id':'sidebar'}), dict(name='div', attrs={'class':'intro'}), dict(name='p', attrs={'class':'bodytext'}), dict(name='div', attrs={'class':'single_image'})] keep_only_tags = [dict(name='div', attrs={'id':'theContent'}), dict(name='div', attrs={'id':'sidebar'}), dict(name='div', attrs={'class':'intro'}), dict(name='p', attrs={'class':'bodytext'}), dict(name='div', attrs={'class':'single_image'})]
@ -61,17 +68,31 @@ class BrandEins(BasicNewsRecipe):
return soup return soup
def get_cover(self, soup):
cover_url = None
cover_item = soup.find('div', attrs = {'class': 'cover_image'})
if cover_item:
cover_url = 'http://www.brandeins.de/' + cover_item.img['src']
return cover_url
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
archive = "http://www.brandeins.de/archiv.html" archive = "http://www.brandeins.de/archiv.html"
issue = self.default_issue
if self.username:
try:
issue = int(self.username)
except:
pass
soup = self.index_to_soup(archive) soup = self.index_to_soup(archive)
latest_jahrgang = soup.findAll('div', attrs={'class': re.compile(r'\bjahrgang-latest\b') })[0].findAll('ul')[0] latest_jahrgang = soup.findAll('div', attrs={'class': re.compile(r'\bjahrgang-latest\b') })[0].findAll('ul')[0]
pre_latest_issue = latest_jahrgang.findAll('a')[len(latest_jahrgang.findAll('a'))-self.which_ausgabe] pre_latest_issue = latest_jahrgang.findAll('a')[len(latest_jahrgang.findAll('a'))-issue]
url = pre_latest_issue.get('href', False) url = pre_latest_issue.get('href', False)
# Get the title for the magazin - build it out of the title of the cover - take the issue and year; # Get the title for the magazin - build it out of the title of the cover - take the issue and year;
self.title = "Brand Eins "+ re.search(r"(?P<date>\d\d\/\d\d\d\d+)", pre_latest_issue.find('img').get('title', False)).group('date') self.title = "brand eins "+ re.search(r"(?P<date>\d\d\/\d\d\d\d)", pre_latest_issue.find('img').get('title', False)).group('date')
url = 'http://brandeins.de/'+url url = 'http://brandeins.de/'+url
# url = "http://www.brandeins.de/archiv/magazin/tierisch.html" # url = "http://www.brandeins.de/archiv/magazin/tierisch.html"
@ -83,6 +104,7 @@ class BrandEins(BasicNewsRecipe):
def brand_eins_parse_latest_issue(self, url): def brand_eins_parse_latest_issue(self, url):
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
self.cover_url = self.get_cover(soup)
article_lists = [soup.find('div', attrs={'class':'subColumnLeft articleList'}), soup.find('div', attrs={'class':'subColumnRight articleList'})] article_lists = [soup.find('div', attrs={'class':'subColumnLeft articleList'}), soup.find('div', attrs={'class':'subColumnRight articleList'})]
titles_and_articles = [] titles_and_articles = []
@ -123,3 +145,4 @@ class BrandEins(BasicNewsRecipe):
current_articles.append({'title': title, 'url': url, 'description': description, 'date':''}) current_articles.append({'title': title, 'url': url, 'description': description, 'date':''})
titles_and_articles.append([chapter_title, current_articles]) titles_and_articles.append([chapter_title, current_articles])
return titles_and_articles return titles_and_articles