gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[tvp] Modernize

Browse source
This commit is contained in:
Tithen-Firion 2014-12-04 14:12:09 +01:00
parent 995ad69c54
commit 2415951ead
1 changed files with 4 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
youtube_dl/extractor/tvp.py
View file

@ -127,26 +127,15 @@ class TvpSeriesIE(InfoExtractor):
} }
] ]
def _force_download_webpage(self, url, v_id, tries=0):
if tries >= 5:
raise ExtractorError(
'%s: Cannot download webpage, try again later' % v_id)
# Sometimes happen, but in my tests second try always succeeded
try:
return self._download_webpage(url, v_id)
except IncompleteRead as e:
return self._force_download_webpage(url, v_id, tries+1)
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._force_download_webpage(url, display_id) webpage = self._download_webpage(url, display_id, tries=5)
title = self._html_search_regex( title = self._html_search_regex(
r'(?s) id=[\'"]path[\'"]>(.*?)</span>', webpage, 'series') r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series')
title = title.split(' / ', 2)[-1]
playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id')
playlist = self._force_download_webpage( playlist = self._download_webpage(
'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend'
'edId=0&sort=&page=0&pageSize=1000000' % playlist_id, display_id) 'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5)
videos_paths = re.findall( videos_paths = re.findall(
'(?s)class="shortTitle">.*?href="(/[^"]+)', playlist) '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
entries = [ entries = [