Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/t3d/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2014-02-25 08:22:34 +05:30
commit 37fcd4093b
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
recipes/gosc_full.recipe
View File

@ -18,11 +18,12 @@ class GN(BasicNewsRecipe):
no_stylesheets = True
language = 'pl'
remove_javascript = True
masthead_url = 'http://m.gosc.pl/static/themes/czerwony_gosc-mobile/logo.png'
def find_last_issue(self):
raw = self.index_to_soup('http://gosc.pl/wyszukaj/wydania/3.Gosc-Niedzielny/', raw=True)
raw = self.index_to_soup('http://m.gosc.pl/wyszukaj/wydania/3.Gosc-Niedzielny/', raw=True)
doc = html.fromstring(raw)
page = doc.xpath('//div[@class="c"]//div[@class="search-result"]/div[1]/div[2]/h1//a/@href')
page = doc.xpath('//div[@class="search-result"]/div[1]/div[1]/a/@href')
if time.strftime("%w") in ['3','4']:
return page[5]
@ -30,7 +31,8 @@ class GN(BasicNewsRecipe):
return page[4]
def parse_index(self):
soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue())
self.last_issue = self.find_last_issue()
soup = self.index_to_soup('http://gosc.pl' + self.last_issue)
self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src']
feeds = []
enlisted = []
@ -42,7 +44,7 @@ class GN(BasicNewsRecipe):
'url' : 'http://www.gosc.pl' + art['href'],
'description' : self.tag_to_string(a.find('p',attrs={'class':'b lead'}))
}]
feeds.append((u'Wstępniak',articles))
feeds.append((u'Na dobry początek',articles))
enlisted.append(articles[0].get('url'))
# columns:
for addr in soup.findAll('a',attrs={'href':re.compile('kategoria')}):
@ -57,7 +59,7 @@ class GN(BasicNewsRecipe):
page = 1
not_assigned = []
while True:
soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue().replace('przeglad','wszystko') + '/' + str(page))
soup = self.index_to_soup('http://gosc.pl' + self.last_issue.replace('przeglad','wszystko') + '/' + str(page))
articles = list(self.find_articles(soup))
not_assigned.extend([x for x in articles if x.get('url') not in enlisted])
page+=1