Merge branch 'dcn' of github.com:remitamine/youtube-dl into remitamine-dcn

This commit is contained in:
remitamine 2015-12-28 10:38:31 +01:00
commit 974c1b2d42
2 changed files with 151 additions and 34 deletions

View file

@ -135,7 +135,12 @@
) )
from .daum import DaumIE from .daum import DaumIE
from .dbtv import DBTVIE from .dbtv import DBTVIE
from .dcn import DCNIE from .dcn import (
DCNIE,
DCNVideoIE,
DCNLiveIE,
DCNSeasonIE,
)
from .dctp import DctpTvIE from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE from .deezer import DeezerPlaylistIE
from .democracynow import DemocracynowIE from .democracynow import DemocracynowIE

View file

@ -1,26 +1,89 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
import base64
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse from ..compat import compat_urllib_parse
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
parse_iso8601, parse_iso8601,
sanitized_Request, sanitized_Request,
smuggle_url,
unsmuggle_url,
) )
class DCNIE(InfoExtractor): class DCNIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
def _real_extract(self, url):
show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
if video_id and int(video_id) > 0:
return self.url_result(
'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://www.dcndigital.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'DCNSeason')
else:
return self.url_result(
'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
class DCNBaseIE(InfoExtractor):
def _extract_video_info(self, video_data, video_id, is_live):
title = video_data.get('title_en') or video_data['title_ar']
img = video_data.get('img')
thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
duration = int_or_none(video_data.get('duration'))
description = video_data.get('description_en') or video_data.get('description_ar')
timestamp = parse_iso8601(video_data.get('create_time'), ' ')
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'is_live': is_live,
}
def _extract_video_formats(self, webpage, video_id, entry_protocol):
formats = []
m3u8_url = self._html_search_regex(
r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False)
if m3u8_url:
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None)
if m3u8_formats:
formats.extend(m3u8_formats)
rtsp_url = self._search_regex(
r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
if rtsp_url:
formats.append({
'url': rtsp_url,
'format_id': 'rtsp',
})
self._sort_formats(formats)
return formats
class DCNVideoIE(DCNBaseIE):
IE_NAME = 'dcn:video'
_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887', 'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
'info_dict': 'info_dict':
{ {
'id': '17375', 'id': '17375',
'ext': 'mp4', 'ext': 'mp4',
'title': 'رحلة العمر : الحلقة 1', 'title': 'رحلة العمر : الحلقة 1',
'description': 'md5:0156e935d870acb8ef0a66d24070c6d6', 'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 2041, 'duration': 2041,
'timestamp': 1227504126, 'timestamp': 1227504126,
'upload_date': '20081124', 'upload_date': '20081124',
@ -37,46 +100,95 @@ def _real_extract(self, url):
request = sanitized_Request( request = sanitized_Request(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id, 'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
headers={'Origin': 'http://www.dcndigital.ae'}) headers={'Origin': 'http://www.dcndigital.ae'})
video_data = self._download_json(request, video_id)
video = self._download_json(request, video_id) info = self._extract_video_info(video_data, video_id, False)
title = video.get('title_en') or video['title_ar']
webpage = self._download_webpage( webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
compat_urllib_parse.urlencode({ compat_urllib_parse.urlencode({
'id': video['id'], 'id': video_data['id'],
'user_id': video['user_id'], 'user_id': video_data['user_id'],
'signature': video['signature'], 'signature': video_data['signature'],
'countries': 'Q0M=', 'countries': 'Q0M=',
'filter': 'DENY', 'filter': 'DENY',
}), video_id) }), video_id)
info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
return info
m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
rtsp_url = self._search_regex( class DCNLiveIE(DCNBaseIE):
r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False) IE_NAME = 'dcn:live'
if rtsp_url: _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
formats.append({
'url': rtsp_url, def _real_extract(self, url):
'format_id': 'rtsp', channel_id = self._match_id(url)
request = sanitized_Request(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
headers={'Origin': 'http://www.dcndigital.ae'})
channel_data = self._download_json(request, channel_id)
info = self._extract_video_info(channel_data, channel_id, True)
webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
compat_urllib_parse.urlencode({
'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
'signature': channel_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
}), channel_id)
info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
return info
class DCNSeasonIE(InfoExtractor):
IE_NAME = 'dcn:season'
_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
_TEST = {
'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
'info_dict':
{
'id': '7910',
'title': 'محاضرات الشيخ الشعراوي',
},
'playlist_mincount': 27,
}
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
show_id, season_id = re.match(self._VALID_URL, url).groups()
data = {}
if season_id:
data['season'] = season_id
show_id = smuggled_data.get('show_id')
if show_id is None:
request = sanitized_Request(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
headers={'Origin': 'http://www.dcndigital.ae'})
season = self._download_json(request, season_id)
show_id = season['id']
data['show_id'] = show_id
request = sanitized_Request(
'http://admin.mangomolo.com/analytics/index.php/plus/show',
compat_urllib_parse.urlencode(data),
{
'Origin': 'http://www.dcndigital.ae',
'Content-Type': 'application/x-www-form-urlencoded'
}) })
self._sort_formats(formats) show = self._download_json(request, show_id)
if not season_id:
season_id = show['default_season']
for season in show['seasons']:
if season['id'] == season_id:
title = season.get('title_en') or season['title_ar']
img = video.get('img') entries = []
thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None for video in show['videos']:
duration = int_or_none(video.get('duration')) entries.append(self.url_result(
description = video.get('description_en') or video.get('description_ar') 'http://www.dcndigital.ae/media/%s' % video['id'], 'DCNVideo'))
timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
return { return self.playlist_result(entries, season_id, title)
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}