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

add articles not assigned to any category

Browse Source
This commit is contained in:
Tomasz Długosz 2014-02-21 03:07:32 +01:00
parent e5cc63b1c6
commit 23249ad434
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/gosc_full.recipe
View File

@ -33,6 +33,7 @@ class GN(BasicNewsRecipe):
soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue()) soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue())
self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src'] self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src']
feeds = [] feeds = []
enlisted = []
# editorial: # editorial:
a = soup.find('div',attrs={'class':'release-wp-b'}) a = soup.find('div',attrs={'class':'release-wp-b'})
art = a.find('a') art = a.find('a')
@ -42,6 +43,7 @@ class GN(BasicNewsRecipe):
'description' : self.tag_to_string(a.find('p',attrs={'class':'b lead'})) 'description' : self.tag_to_string(a.find('p',attrs={'class':'b lead'}))
}] }]
feeds.append((u'Wstępniak',articles)) feeds.append((u'Wstępniak',articles))
enlisted.append(articles[0].get('url'))
# columns: # columns:
for addr in soup.findAll('a',attrs={'href':re.compile('kategoria')}): for addr in soup.findAll('a',attrs={'href':re.compile('kategoria')}):
if addr.string != u'wszystkie artyku\u0142y z tej kategorii \xbb': if addr.string != u'wszystkie artyku\u0142y z tej kategorii \xbb':
@ -50,6 +52,20 @@ class GN(BasicNewsRecipe):
if len(articles) > 0: if len(articles) > 0:
section = addr.string section = addr.string
feeds.append((section, articles)) feeds.append((section, articles))
enlisted.extend(list(article.get('url') for article in articles))
# not assigned content:
page = 1
not_assigned = []
while True:
soup = self.index_to_soup('http://gosc.pl' + self.find_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
pages = soup.find('span', attrs={'class':'pgr_nrs'})
if str(page) not in [self.tag_to_string(x)[1] for x in pages.findAll('a')]:
break
feeds.insert(1,(u'Nieprzypisane', not_assigned))
return feeds return feeds
def find_articles(self, main_block): def find_articles(self, main_block):