R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #2 from mrfade/kanald

Browse Source 
fix extraction
This commit is contained in:
kosantosbik 2019-05-06 21:03:16 +03:00 committed by GitHub
commit 5145ae5d49
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/kanald.py
View File

@ -4,7 +4,10 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import merge_dicts from ..utils import (
merge_dicts,
try_get,
)
class KanaldBaseIE(InfoExtractor): class KanaldBaseIE(InfoExtractor):
@ -20,15 +23,17 @@ class KanaldBaseIE(InfoExtractor):
"""FIXME: https://www.kanald.com.tr/kuzeyguney/80-bolum-izle/19364 -> Invalid control character at: line 5 column 146 (char 255)""" """FIXME: https://www.kanald.com.tr/kuzeyguney/80-bolum-izle/19364 -> Invalid control character at: line 5 column 146 (char 255)"""
json_ld = self._search_regex( search_json_ld = self._search_regex(
r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?:\s+)?(?P<json_ld>{[^<]+VideoObject[^<]+})(?:\s+)?</script>', webpage, 'JSON-LD', group='json_ld') r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?:\s+)?(?P<json_ld>{[^<]+VideoObject[^<]+})(?:\s+)?</script>', webpage, 'JSON-LD', group='json_ld')
ld_info = self._json_ld(json_ld, video_id) json_ld = self._parse_json(search_json_ld, video_id)
if not re.match(r'dogannet\.tv', ld_info['url']): if not re.match(r'dogannet\.tv', json_ld['contentUrl']):
ld_info.update({ json_ld.update({
'url': 'https://soledge13.dogannet.tv/%s' % ld_info['url'] 'contentUrl': 'https://soledge13.dogannet.tv/%s' % json_ld['contentUrl']
}) })
ld_info = self._json_ld(json_ld, video_id)
return merge_dicts(ld_info, info) return merge_dicts(ld_info, info)
@ -118,7 +123,7 @@ class KanaldSerieIE(InfoExtractor):
continue continue
for episode_url in episode_urls: for episode_url in episode_urls:
episode_url = episode_url[1] episode_url = try_get(episode_url, lambda x: x[1])
if not episode_url: if not episode_url:
continue continue
yield self.url_result( yield self.url_result(