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

fix fetching articles

Browse Source
This commit is contained in:
Tomasz Długosz 2018-10-06 23:20:56 +02:00
parent 9aa202d7bc
commit ec5fea9c5e
1 changed files with 1 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
recipes/tanuki.recipe
View File

@ -11,6 +11,7 @@ class tanuki(BasicNewsRecipe):
language = 'pl' language = 'pl'
max_articles_per_feed = 100 max_articles_per_feed = 100
encoding = 'utf-8' encoding = 'utf-8'
autocleanup = True
extra_css = 'ul {list-style: none; padding: 0; margin: 0;} .kadr{float: left;} .dwazdania {float: right;}' extra_css = 'ul {list-style: none; padding: 0; margin: 0;} .kadr{float: left;} .dwazdania {float: right;}'
preprocess_regexps = [(re.compile(u'<h3><a class="screen".*?</h3>', re.DOTALL), lambda match: ''), (re.compile( preprocess_regexps = [(re.compile(u'<h3><a class="screen".*?</h3>', re.DOTALL), lambda match: ''), (re.compile(
unicode(r'<div><a href="/strony/((manga)|(anime))/[0-9]+?/oceny(\-redakcji){0,1}">Zobacz jak ocenili</a></div>'), re.DOTALL), lambda match: '')] unicode(r'<div><a href="/strony/((manga)|(anime))/[0-9]+?/oceny(\-redakcji){0,1}">Zobacz jak ocenili</a></div>'), re.DOTALL), lambda match: '')]
@ -42,15 +43,3 @@ class tanuki(BasicNewsRecipe):
appendtag.insert(pos, pagetext) appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class': 'nextarrow'}): for r in appendtag.findAll(attrs={'class': 'nextarrow'}):
r.extract() r.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
if 'tanuki-anime' in soup.title.string.lower():
a['href'] = 'http://anime.tanuki.pl' + a['href']
elif 'tanuki-manga' in soup.title.string.lower():
a['href'] = 'http://manga.tanuki.pl' + a['href']
elif 'tanuki-czytelnia' in soup.title.string.lower():
a['href'] = 'http://czytelnia.tanuki.pl' + a['href']
return soup