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

[tvanouvelles] Changed the regex. Also kept the original text encoding for the description and title.

Browse Source
This commit is contained in:
Jean-Nicolas 2016-09-12 20:28:12 -04:00
parent e12ade612f
commit 7ca31fa7f6
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
youtube_dl/extractor/tvanouvelles.py
View File

@ -1,18 +1,19 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
class TVANouvellesIE(InfoExtractor): class TVANouvellesIE(InfoExtractor):
_VALID_URL = r'https?://(www\.|)tvanouvelles\.(ca|com|qc)/.*.?/(?P<id>[^/]+)' _VALID_URL = r'https?://[[\w].*]?tvanouvelles\.ca/.*?/(?P<id>[^/]+)/?$'
_TEST = { _TEST = {
'url': 'http://www.tvanouvelles.ca/videos/5117035533001', 'url': 'http://www.tvanouvelles.ca/videos/5117035533001',
'info_dict': { 'info_dict': {
'id': '5117035533001', 'id': '5117035533001',
'ext': 'mp4', 'ext': 'mp4',
'title': 'L\u2019industrie du taxi d\xe9nonce l\u2019entente entre Qu\xe9bec et Uber: explications', 'title': 'L’industrie du taxi dénonce l’entente entre Québec et Uber - explications',
'description': 'L\u2019industrie du taxi a unanimement a d\xe9nonc\xe9 l\u2019entente avec le gouvernement du Qu\xe9bec qui permet \xe0 l\u2019entreprise de covoiturage Uber de faire des affaires l\xe9galement dans le cadre d\u2019un projet pilote d\u2019un an.', 'description': '"L’industrie du taxi a unanimement a dénoncé l’entente avec le gouvernement du Québec qui permet à l’entreprise de covoiturage Uber de faire des affaires légalement dans le cadre d’un projet pilote d’un an.',
'uploader_id': '1741764581', 'uploader_id': '1741764581',
'timestamp': 1473352030, 'timestamp': 1473352030,
'upload_date': '20160908', 'upload_date': '20160908',
@ -26,5 +27,5 @@ class TVANouvellesIE(InfoExtractor):
program_name = self._match_id(url) program_name = self._match_id(url)
webpage = self._download_webpage(url, program_name) webpage = self._download_webpage(url, program_name)
brightcove_id = self._search_regex( brightcove_id = self._search_regex(
r'data-video-id\=(.+[0-9]?)', webpage, 'brightcove id') r'data-video-id\=["\']?(.+[0-9])["\']?', webpage, 'brightcove id')
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)