[bet] Use unique part of xml url as the video id and fix tests (closes #5642)

The guid changes often.
pull/5642/merge
blissland 2015-05-07 16:56:15 +01:00 committed by Jaime Marquínez Ferrándiz
parent 541168039d
commit 249962ffa2
1 changed files with 7 additions and 6 deletions

View File

@ -16,11 +16,11 @@ class BetIE(InfoExtractor):
{ {
'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html', 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
'info_dict': { 'info_dict': {
'id': '740ab250-bb94-4a8a-8787-fe0de7c74471', 'id': 'news/national/2014/a-conversation-with-president-obama',
'display_id': 'in-bet-exclusive-obama-talks-race-and-racism', 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
'ext': 'flv', 'ext': 'flv',
'title': 'BET News Presents: A Conversation With President Obama', 'title': 'A Conversation With President Obama',
'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6', 'description': 'md5:699d0652a350cf3e491cd15cc745b5da',
'duration': 1534, 'duration': 1534,
'timestamp': 1418075340, 'timestamp': 1418075340,
'upload_date': '20141208', 'upload_date': '20141208',
@ -35,7 +35,7 @@ class BetIE(InfoExtractor):
{ {
'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
'info_dict': { 'info_dict': {
'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d', 'id': 'news/national/2014/justice-for-ferguson-a-community-reacts',
'display_id': 'justice-for-ferguson-a-community-reacts', 'display_id': 'justice-for-ferguson-a-community-reacts',
'ext': 'flv', 'ext': 'flv',
'title': 'Justice for Ferguson: A Community Reacts', 'title': 'Justice for Ferguson: A Community Reacts',
@ -61,6 +61,9 @@ class BetIE(InfoExtractor):
[r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
webpage, 'media URL')) webpage, 'media URL'))
video_id = self._search_regex(
r'/video/(.*)/_jcr_content/', media_url, 'video id')
mrss = self._download_xml(media_url, display_id) mrss = self._download_xml(media_url, display_id)
item = mrss.find('./channel/item') item = mrss.find('./channel/item')
@ -75,8 +78,6 @@ class BetIE(InfoExtractor):
description = xpath_text( description = xpath_text(
item, './description', 'description', fatal=False) item, './description', 'description', fatal=False)
video_id = xpath_text(item, './guid', 'video id', fatal=False)
timestamp = parse_iso8601(xpath_text( timestamp = parse_iso8601(xpath_text(
item, xpath_with_ns('./dc:date', NS_MAP), item, xpath_with_ns('./dc:date', NS_MAP),
'upload date', fatal=False)) 'upload date', fatal=False))