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

[twentymin] Fixed 20min information extractor. Tried to add better video description handler, but the site seems to be too inconsistent...

Browse Source
This commit is contained in:
Alex Seiler 2017-01-11 19:17:05 +01:00
parent 69807d59ed
commit eaffc609a7
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/twentymin.py
View File

@ -4,7 +4,12 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import remove_end from ..utils import (
remove_end,
ExtractorError,
clean_html,
get_element_by_class
)
class TwentyMinutenIE(InfoExtractor): class TwentyMinutenIE(InfoExtractor):
@ -99,10 +104,16 @@ class TwentyMinutenIE(InfoExtractor):
r'.*videoId@(\d+)', r'.*videoId@(\d+)',
params, 'Video Id', default=None) if params is not None else '' params, 'Video Id', default=None) if params is not None else ''
print('VIDEO ID: {}'.format(video_id)) print('VIDEO ID: {}'.format(video_id))
if not video_id: # the article does not contain a video
raise ExtractorError('No media links found on %s.' % url, expected=True)
# # Try to use the real video description:
description = self._html_search_meta( # description = clean_html(get_element_by_class('caption', webpage))
'description', webpage, 'description') # # Otherwise, use the lead text of the article as the video description:
# if not description:
# description = self._html_search_meta(
# 'description', webpage, 'description')
description = self._html_search_meta('description', webpage, 'description')
print('DESCRIPTION: {}'.format(description)) print('DESCRIPTION: {}'.format(description))
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
print('THUMBNAIL: {}'.format(thumbnail)) print('THUMBNAIL: {}'.format(thumbnail))