w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[mangomolo] fix video format extraction and add support for player URLs

Browse source
This commit is contained in:
Remita Amine 2019-10-17 13:21:44 +01:00
parent 86f63633c8
commit 755541a4c8
2 changed files with 17 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

8
youtube_dl/extractor/generic.py
View file

@ -2962,10 +2962,14 @@ class GenericIE(InfoExtractor):
# Look for Mangomolo embeds # Look for Mangomolo embeds
mobj = re.search( mobj = re.search(
r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/ r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
(?:
admin\.mangomolo\.com/analytics/index\.php/customers/embed|
player\.mangomolo\.com/v1
)/
(?: (?:
video\?.*?\bid=(?P<video_id>\d+)| video\?.*?\bid=(?P<video_id>\d+)|
index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
).+?)\1''', webpage) ).+?)\1''', webpage)
if mobj is not None: if mobj is not None:
info = { info = {

17
youtube_dl/extractor/mangomolo.py
View file

@ -10,18 +10,21 @@ from ..utils import int_or_none
class MangomoloBaseIE(InfoExtractor): class MangomoloBaseIE(InfoExtractor):
_BASE_REGEX = r'https?://(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)'
def _get_real_id(self, page_id): def _get_real_id(self, page_id):
return page_id return page_id
def _real_extract(self, url): def _real_extract(self, url):
page_id = self._get_real_id(self._match_id(url)) page_id = self._get_real_id(self._match_id(url))
webpage = self._download_webpage(url, page_id) webpage = self._download_webpage(
'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id)
hidden_inputs = self._hidden_inputs(webpage) hidden_inputs = self._hidden_inputs(webpage)
m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native' m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native'
format_url = self._html_search_regex( format_url = self._html_search_regex(
[ [
r'file\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)',
r'<a[^>]+href="(rtsp://[^"]+)"' r'<a[^>]+href="(rtsp://[^"]+)"'
], webpage, 'format url') ], webpage, 'format url')
formats = self._extract_wowza_formats( formats = self._extract_wowza_formats(
@ -39,14 +42,16 @@ class MangomoloBaseIE(InfoExtractor):
class MangomoloVideoIE(MangomoloBaseIE): class MangomoloVideoIE(MangomoloBaseIE):
IE_NAME = 'mangomolo:video' _TYPE = 'video'
_VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)' IE_NAME = 'mangomolo:' + _TYPE
_VALID_URL = MangomoloBaseIE._BASE_REGEX + r'video\?.*?\bid=(?P<id>\d+)'
_IS_LIVE = False _IS_LIVE = False
class MangomoloLiveIE(MangomoloBaseIE): class MangomoloLiveIE(MangomoloBaseIE):
IE_NAME = 'mangomolo:live' _TYPE = 'live'
_VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' IE_NAME = 'mangomolo:' + _TYPE
_VALID_URL = MangomoloBaseIE._BASE_REGEX + r'(live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
_IS_LIVE = True _IS_LIVE = True
def _get_real_id(self, page_id): def _get_real_id(self, page_id):