Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated Brand Eins

Browse Source
This commit is contained in:
Kovid Goyal 2011-01-01 10:45:27 -07:00
parent bac39367b5
commit 941d5dbda5
1 changed files with 29 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
resources/recipes/brand_eins.recipe
View File

@ -1,19 +1,16 @@
#!/usr/bin/env python
# -*- 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'
__copyright__ = '2010, Constantin Hofstetter <consti at consti.de>, Steffen Siebert <calibre at steffensiebert.de>'
__version__ = '0.96'
__version__ = '0.97'
''' http://brandeins.de - Wirtschaftsmagazin '''
import re
import string
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.recipes import BasicNewsRecipe
class BrandEins(BasicNewsRecipe):
title = u'brand eins'
@ -28,6 +25,8 @@ class BrandEins(BasicNewsRecipe):
language = 'de'
publication_type = 'magazine'
needs_subscription = 'optional'
# Prevent that conversion date is appended to title
timefmt = ''
# 2 is the last full magazine (default)
# 1 is the newest (but not full)
@ -66,6 +65,13 @@ class BrandEins(BasicNewsRecipe):
new_p = "<p><i>"+ content +"</i></p>"
p.replaceWith(new_p)
# Change <h3> to <h1>
header = soup.find("h3")
if header:
tag = Tag(soup, "h1")
tag.insert(0, header.contents[0])
header.replaceWith(tag)
return soup
def get_cover(self, soup):
@ -77,6 +83,7 @@ class BrandEins(BasicNewsRecipe):
def parse_index(self):
feeds = []
issue_map = {}
archive = "http://www.brandeins.de/archiv.html"
@ -88,21 +95,31 @@ class BrandEins(BasicNewsRecipe):
pass
soup = self.index_to_soup(archive)
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'))-issue]
url = pre_latest_issue.get('href', False)
# Get month and year of the magazine issue - build it out of the title of the cover
self.timefmt = " " + re.search(r"(?P<date>\d\d\/\d\d\d\d)", pre_latest_issue.find('img').get('title', False)).group('date')
issue_list = soup.findAll('div', attrs={'class': 'tx-brandeinsmagazine-pi1'})[0].findAll('a')
issue_list = [i for i in issue_list if i.get('onmouseover', False)]
for i in issue_list:
issue_number_string = i.get('onmouseover', False)
if issue_number_string:
match = re.match("^switch_magazine\(([0-9]+), ([0-9]+)\)$", issue_number_string)
issue_number = "%04i%02i" % (int(match.group(1)), int(match.group(2)))
issue_map[issue_number] = i
keys = issue_map.keys()
keys.sort()
keys.reverse()
selected_issue = issue_map[keys[issue-1]]
url = selected_issue.get('href', False)
# 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)", selected_issue.find('img').get('title', False)).group('date')
url = 'http://brandeins.de/'+url
# url = "http://www.brandeins.de/archiv/magazin/tierisch.html"
titles_and_articles = self.brand_eins_parse_latest_issue(url)
titles_and_articles = self.brand_eins_parse_issue(url)
if titles_and_articles:
for title, articles in titles_and_articles:
feeds.append((title, articles))
return feeds
def brand_eins_parse_latest_issue(self, url):
def brand_eins_parse_issue(self, 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'})]
@ -145,4 +162,3 @@ class BrandEins(BasicNewsRecipe):
current_articles.append({'title': title, 'url': url, 'description': description, 'date':''})
titles_and_articles.append([chapter_title, current_articles])
return titles_and_articles