|
@ -1,31 +1,27 @@ |
|
|
from __future__ import unicode_literals |
|
|
from __future__ import unicode_literals |
|
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
|
|
|
from ..compat import compat_urllib_parse_unquote |
|
|
|
|
|
from ..utils import ( |
|
|
|
|
|
xpath_text, |
|
|
|
|
|
xpath_with_ns, |
|
|
|
|
|
int_or_none, |
|
|
|
|
|
parse_iso8601, |
|
|
|
|
|
) |
|
|
|
|
|
|
|
|
from .mtv import MTVServicesInfoExtractor |
|
|
|
|
|
from ..utils import unified_strdate |
|
|
|
|
|
from ..compat import compat_urllib_parse_urlencode |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class BetIE(InfoExtractor): |
|
|
|
|
|
|
|
|
class BetIE(MTVServicesInfoExtractor): |
|
|
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' |
|
|
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' |
|
|
_TESTS = [ |
|
|
_TESTS = [ |
|
|
{ |
|
|
{ |
|
|
'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': 'news/national/2014/a-conversation-with-president-obama', |
|
|
|
|
|
|
|
|
'id': '07e96bd3-8850-3051-b856-271b457f0ab8', |
|
|
'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': 'A Conversation With President Obama', |
|
|
'title': 'A Conversation With President Obama', |
|
|
'description': 'md5:699d0652a350cf3e491cd15cc745b5da', |
|
|
|
|
|
|
|
|
'description': 'President Obama urges persistence in confronting racism and bias.', |
|
|
'duration': 1534, |
|
|
'duration': 1534, |
|
|
'timestamp': 1418075340, |
|
|
|
|
|
'upload_date': '20141208', |
|
|
'upload_date': '20141208', |
|
|
'uploader': 'admin', |
|
|
|
|
|
'thumbnail': 're:(?i)^https?://.*\.jpg$', |
|
|
'thumbnail': 're:(?i)^https?://.*\.jpg$', |
|
|
|
|
|
'subtitles': { |
|
|
|
|
|
'en': 'mincount:2', |
|
|
|
|
|
} |
|
|
}, |
|
|
}, |
|
|
'params': { |
|
|
'params': { |
|
|
# rtmp download |
|
|
# rtmp download |
|
@ -35,16 +31,17 @@ 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': 'news/national/2014/justice-for-ferguson-a-community-reacts', |
|
|
|
|
|
|
|
|
'id': '9f516bf1-7543-39c4-8076-dd441b459ba9', |
|
|
'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', |
|
|
'description': 'A BET News special.', |
|
|
'description': 'A BET News special.', |
|
|
'duration': 1696, |
|
|
'duration': 1696, |
|
|
'timestamp': 1416942360, |
|
|
|
|
|
'upload_date': '20141125', |
|
|
'upload_date': '20141125', |
|
|
'uploader': 'admin', |
|
|
|
|
|
'thumbnail': 're:(?i)^https?://.*\.jpg$', |
|
|
'thumbnail': 're:(?i)^https?://.*\.jpg$', |
|
|
|
|
|
'subtitles': { |
|
|
|
|
|
'en': 'mincount:2', |
|
|
|
|
|
} |
|
|
}, |
|
|
}, |
|
|
'params': { |
|
|
'params': { |
|
|
# rtmp download |
|
|
# rtmp download |
|
@ -53,57 +50,32 @@ class BetIE(InfoExtractor): |
|
|
} |
|
|
} |
|
|
] |
|
|
] |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
|
|
|
display_id = self._match_id(url) |
|
|
|
|
|
webpage = self._download_webpage(url, display_id) |
|
|
|
|
|
|
|
|
|
|
|
media_url = compat_urllib_parse_unquote(self._search_regex( |
|
|
|
|
|
[r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], |
|
|
|
|
|
webpage, 'media URL')) |
|
|
|
|
|
|
|
|
_FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player" |
|
|
|
|
|
|
|
|
video_id = self._search_regex( |
|
|
|
|
|
r'/video/(.*)/_jcr_content/', media_url, 'video id') |
|
|
|
|
|
|
|
|
def _get_feed_query(self, uri): |
|
|
|
|
|
return compat_urllib_parse_urlencode({ |
|
|
|
|
|
'uuid': uri, |
|
|
|
|
|
}) |
|
|
|
|
|
|
|
|
mrss = self._download_xml(media_url, display_id) |
|
|
|
|
|
|
|
|
|
|
|
item = mrss.find('./channel/item') |
|
|
|
|
|
|
|
|
|
|
|
NS_MAP = { |
|
|
|
|
|
'dc': 'http://purl.org/dc/elements/1.1/', |
|
|
|
|
|
'media': 'http://search.yahoo.com/mrss/', |
|
|
|
|
|
'ka': 'http://kickapps.com/karss', |
|
|
|
|
|
} |
|
|
|
|
|
|
|
|
def _extract_mgid(self, webpage): |
|
|
|
|
|
return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid') |
|
|
|
|
|
|
|
|
title = xpath_text(item, './title', 'title') |
|
|
|
|
|
description = xpath_text( |
|
|
|
|
|
item, './description', 'description', fatal=False) |
|
|
|
|
|
|
|
|
|
|
|
timestamp = parse_iso8601(xpath_text( |
|
|
|
|
|
item, xpath_with_ns('./dc:date', NS_MAP), |
|
|
|
|
|
'upload date', fatal=False)) |
|
|
|
|
|
uploader = xpath_text( |
|
|
|
|
|
item, xpath_with_ns('./dc:creator', NS_MAP), |
|
|
|
|
|
'uploader', fatal=False) |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
|
|
|
display_id = self._match_id(url) |
|
|
|
|
|
|
|
|
media_content = item.find( |
|
|
|
|
|
xpath_with_ns('./media:content', NS_MAP)) |
|
|
|
|
|
duration = int_or_none(media_content.get('duration')) |
|
|
|
|
|
smil_url = media_content.get('url') |
|
|
|
|
|
|
|
|
webpage = self._download_webpage(url, display_id) |
|
|
|
|
|
mgid = self._extract_mgid(webpage) |
|
|
|
|
|
videos_info = self._get_videos_info(mgid) |
|
|
|
|
|
|
|
|
thumbnail = media_content.find( |
|
|
|
|
|
xpath_with_ns('./media:thumbnail', NS_MAP)).get('url') |
|
|
|
|
|
|
|
|
info_dict = videos_info['entries'][0] |
|
|
|
|
|
|
|
|
formats = self._extract_smil_formats(smil_url, display_id) |
|
|
|
|
|
self._sort_formats(formats) |
|
|
|
|
|
|
|
|
upload_date = unified_strdate(self._html_search_meta('date', webpage)) |
|
|
|
|
|
description = self._html_search_meta('description', webpage) |
|
|
|
|
|
|
|
|
return { |
|
|
|
|
|
'id': video_id, |
|
|
|
|
|
|
|
|
info_dict.update({ |
|
|
'display_id': display_id, |
|
|
'display_id': display_id, |
|
|
'title': title, |
|
|
|
|
|
'description': description, |
|
|
'description': description, |
|
|
'thumbnail': thumbnail, |
|
|
|
|
|
'timestamp': timestamp, |
|
|
|
|
|
'uploader': uploader, |
|
|
|
|
|
'duration': duration, |
|
|
|
|
|
'formats': formats, |
|
|
|
|
|
} |
|
|
|
|
|
|
|
|
'upload_date': upload_date, |
|
|
|
|
|
}) |
|
|
|
|
|
|
|
|
|
|
|
return info_dict |