github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[svtplay:series] Improve extraction (closes #16059)

Browse source
This commit is contained in:
Sergey M․ 2018-04-04 23:52:00 +07:00
parent fd97fa7bfc
commit b71bb3ba8b
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 18 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
youtube_dl/extractor/extractors.py
View file

@ -1031,7 +1031,7 @@
from .svt import ( from .svt import (
SVTIE, SVTIE,
SVTPlayIE, SVTPlayIE,
SVTPlaylistIE, SVTSeriesIE,
) )
from .swrmediathek import SWRMediathekIE from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE from .syfy import SyfyIE

36
youtube_dl/extractor/svt.py
View file

@ -193,10 +193,8 @@ def _real_extract(self, url):
return info_dict return info_dict
class SVTPlaylistIE(InfoExtractor): class SVTSeriesIE(InfoExtractor):
IE_DESC = 'SVT Play serie'
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)' _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)'
IE_NAME = 'svtplay:serie'
_TESTS = [{ _TESTS = [{
'url': 'https://www.svtplay.se/rederiet', 'url': 'https://www.svtplay.se/rederiet',
'info_dict': { 'info_dict': {
@ -209,33 +207,28 @@ class SVTPlaylistIE(InfoExtractor):
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTPlaylistIE, cls).suitable(url) return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
page = self._download_webpage( webpage = self._download_webpage(
url, video_id, url, video_id, 'Downloading serie page')
note='Downloading serie page',
errnote='unable to fetch serie page')
root_json = self._search_regex( root = self._parse_json(
r'root\[\'__svtplay\'\]\s*=(.+);\n', self._search_regex(
page, 'root') r'root\[\s*(["\'])_*svtplay\1\s*\]\s*=\s*(?P<json>{.+?})\s*;\s*\n',
root = self._parse_json(root_json, video_id) webpage, 'content', group='json'),
video_id)
metadata = root.get('metaData', {})
related_videos_accordion = root['relatedVideoContent']['relatedVideosAccordion']
entries = [] entries = []
for season in related_videos_accordion: for season in root['relatedVideoContent']['relatedVideosAccordion']:
videos = season.get('videos') videos = season.get('videos')
if not isinstance(videos, list): if not isinstance(videos, list):
continue continue
for video in videos: for video in videos:
content_url = video.get('contentUrl') content_url = video.get('contentUrl')
if not isinstance(content_url, compat_str): if not content_url or not isinstance(content_url, compat_str):
continue continue
entries.append( entries.append(
self.url_result( self.url_result(
@ -244,5 +237,10 @@ def _real_extract(self, url):
video_title=video.get('title') video_title=video.get('title')
)) ))
metadata = root.get('metaData')
if not isinstance(metadata, dict):
metadata = {}
return self.playlist_result( return self.playlist_result(
entries, video_id, metadata.get('title'), metadata.get('description')) entries, video_id, metadata.get('title'),
metadata.get('description'))