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

recipes: gosc_niedzielny - add content not assigned to columns

Browse Source
This commit is contained in:
Tomasz Długosz 2016-10-16 22:38:03 +02:00
parent 9c7f9e5786
commit 298d7cec05
1 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
recipes/gosc_niedzielny.recipe
View File

@ -19,6 +19,7 @@ class GN(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
language = 'pl' language = 'pl'
remove_javascript = True remove_javascript = True
ignore_duplicate_articles = {'url'}
masthead_url = 'http://m.gosc.pl/static/themes/czerwony_gosc-mobile/logo.png' masthead_url = 'http://m.gosc.pl/static/themes/czerwony_gosc-mobile/logo.png'
def find_last_issue(self): def find_last_issue(self):
@ -46,7 +47,7 @@ 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'Na dobry początek', articles)) feeds.append((u'Na dobry początek', articles))
# kategorie # 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':
main_block = self.index_to_soup( main_block = self.index_to_soup(
@ -55,6 +56,20 @@ 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))
# not assigned content:
page = 1
not_assigned = []
while True:
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(articles)
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.append((u'Nieprzypisane', not_assigned))
return feeds return feeds
def find_articles(self, main_block): def find_articles(self, main_block):