ansol/youtube-dl
7
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-20 12:04:03 +00:00
Code Issues Projects Releases Wiki Activity

[ivi:compilation] Fix extraction

Browse Source
This commit is contained in:
Sergey M․ 2016-01-04 03:49:18 +06:00
parent ab3176af34
commit c6270b2ed5
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
youtube_dl/extractor/ivi.py
View File

@ -146,8 +146,11 @@ class IviCompilationIE(InfoExtractor):
}] }]
def _extract_entries(self, html, compilation_id): def _extract_entries(self, html, compilation_id):
return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') return [
for serie in re.findall(r'<strong><a href="/watch/%s/(\d+)">(?:[^<]+)</a></strong>' % compilation_id, html)] self.url_result(
'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
for serie in re.findall(
r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -155,7 +158,8 @@ class IviCompilationIE(InfoExtractor):
season_id = mobj.group('seasonid') season_id = mobj.group('seasonid')
if season_id is not None: # Season link if season_id is not None: # Season link
season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) season_page = self._download_webpage(
url, compilation_id, 'Downloading season %s web page' % season_id)
playlist_id = '%s/season%s' % (compilation_id, season_id) playlist_id = '%s/season%s' % (compilation_id, season_id)
playlist_title = self._html_search_meta('title', season_page, 'title') playlist_title = self._html_search_meta('title', season_page, 'title')
entries = self._extract_entries(season_page, compilation_id) entries = self._extract_entries(season_page, compilation_id)
@ -163,8 +167,9 @@ class IviCompilationIE(InfoExtractor):
compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
playlist_id = compilation_id playlist_id = compilation_id
playlist_title = self._html_search_meta('title', compilation_page, 'title') playlist_title = self._html_search_meta('title', compilation_page, 'title')
seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page) seasons = re.findall(
if len(seasons) == 0: # No seasons in this compilation r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
if not seasons: # No seasons in this compilation
entries = self._extract_entries(compilation_page, compilation_id) entries = self._extract_entries(compilation_page, compilation_id)
else: else:
entries = [] entries = []