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

Fixed regex and retrieval of optional fields

Browse Source
This commit is contained in:
luceatnobis 2017-07-04 20:11:39 +02:00
parent a5c668a0af
commit 7df3f4561e
1 changed files with 16 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/extractor/rutube.py
View File

@ -11,6 +11,7 @@ from ..compat import (
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
unified_strdate, unified_strdate,
try_get,
) )
@ -205,7 +206,7 @@ class RutubePlaylistIE(InfoExtractor):
'playlist_count': 25, 'playlist_count': 25,
}] }]
_VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})/.+pl_id=(?P<pl_id>\d+).*$' _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.+pl_id=(?P<pl_id>\d+).*$'
_PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/source/%s/?page=%s' _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/source/%s/?page=%s'
def _real_extract(self, url): def _real_extract(self, url):
@ -214,6 +215,7 @@ class RutubePlaylistIE(InfoExtractor):
return self._extract_playlist(playlist_id) return self._extract_playlist(playlist_id)
def _extract_playlist(self, playlist_id): def _extract_playlist(self, playlist_id):
import pdb
entries = [] entries = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
page_url = self._PAGE_TEMPLATE % (playlist_id, pagenum) page_url = self._PAGE_TEMPLATE % (playlist_id, pagenum)
@ -229,20 +231,20 @@ class RutubePlaylistIE(InfoExtractor):
results = page['results'] results = page['results']
for result in results: for result in results:
entry = self.url_result(result['video_url'], 'Rutube') entry = self.url_result(result.get('video_url'), 'Rutube')
entry['id'] = result['id'] entry['id'] = result['id']
entry['uploader'] = result['author']['name'] entry['uploader'] = try_get(result, lambda x: x['author']['name'])
entry['uploader_id'] = result['author']['id'] entry['uploader_id'] = try_get(result, lambda x: x['author']['id'])
entry['upload_date'] = unified_strdate(result['created_ts']) entry['upload_date'] = unified_strdate(result.get('created_ts'))
entry['title'] = result['title'] entry['title'] = result.get('title')
entry['description'] = result['description'] entry['description'] = result.get('description')
entry['thumbnail'] = result['thumbnail_url'] entry['thumbnail'] = result.get('thumbnail_url')
entry['duration'] = result['duration'] entry['duration'] = result.get('duration')
entry['category'] = result['category']['name'] entry['category'] = try_get(result, lambda x: x['category']['name'])
entry['age_limit'] = 18 if result['is_adult'] else 0 entry['age_limit'] = 18 if result.get('is_adult') else 0
entry['view_count'] = result['hits'] entry['view_count'] = result.get('hits')
entry['is_live'] = result['is_livestream'] entry['is_live'] = result.get('is_livestream')
entry['webpage_url'] = result['video_url'] entry['webpage_url'] = result.get('video_url')
entries.append(entry) entries.append(entry)
if page['has_next'] is False: if page['has_next'] is False: