youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

awaan.py (7234B)

      1 # coding: utf-8
      2 from __future__ import unicode_literals
      3 
      4 import re
      5 import base64
      6 
      7 from .common import InfoExtractor
      8 from ..compat import (
      9     compat_urllib_parse_urlencode,
     10     compat_str,
     11 )
     12 from ..utils import (
     13     int_or_none,
     14     parse_iso8601,
     15     smuggle_url,
     16     unsmuggle_url,
     17     urlencode_postdata,
     18 )
     19 
     20 
     21 class AWAANIE(InfoExtractor):
     22     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
     23 
     24     def _real_extract(self, url):
     25         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
     26         if video_id and int(video_id) > 0:
     27             return self.url_result(
     28                 'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
     29         elif season_id and int(season_id) > 0:
     30             return self.url_result(smuggle_url(
     31                 'http://awaan.ae/program/season/%s' % season_id,
     32                 {'show_id': show_id}), 'AWAANSeason')
     33         else:
     34             return self.url_result(
     35                 'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
     36 
     37 
     38 class AWAANBaseIE(InfoExtractor):
     39     def _parse_video_data(self, video_data, video_id, is_live):
     40         title = video_data.get('title_en') or video_data['title_ar']
     41         img = video_data.get('img')
     42 
     43         return {
     44             'id': video_id,
     45             'title': self._live_title(title) if is_live else title,
     46             'description': video_data.get('description_en') or video_data.get('description_ar'),
     47             'thumbnail': 'http://admin.mangomolo.com/analytics/%s' % img if img else None,
     48             'duration': int_or_none(video_data.get('duration')),
     49             'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
     50             'is_live': is_live,
     51             'uploader_id': video_data.get('user_id'),
     52         }
     53 
     54 
     55 class AWAANVideoIE(AWAANBaseIE):
     56     IE_NAME = 'awaan:video'
     57     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
     58     _TESTS = [{
     59         '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',
     60         'md5': '5f61c33bfc7794315c671a62d43116aa',
     61         'info_dict':
     62         {
     63             'id': '17375',
     64             'ext': 'mp4',
     65             'title': 'رحلة العمر : الحلقة 1',
     66             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
     67             'duration': 2041,
     68             'timestamp': 1227504126,
     69             'upload_date': '20081124',
     70             'uploader_id': '71',
     71         },
     72     }, {
     73         'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
     74         'only_matching': True,
     75     }]
     76 
     77     def _real_extract(self, url):
     78         video_id = self._match_id(url)
     79 
     80         video_data = self._download_json(
     81             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
     82             video_id, headers={'Origin': 'http://awaan.ae'})
     83         info = self._parse_video_data(video_data, video_id, False)
     84 
     85         embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
     86             'id': video_data['id'],
     87             'user_id': video_data['user_id'],
     88             'signature': video_data['signature'],
     89             'countries': 'Q0M=',
     90             'filter': 'DENY',
     91         })
     92         info.update({
     93             '_type': 'url_transparent',
     94             'url': embed_url,
     95             'ie_key': 'MangomoloVideo',
     96         })
     97         return info
     98 
     99 
    100 class AWAANLiveIE(AWAANBaseIE):
    101     IE_NAME = 'awaan:live'
    102     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
    103     _TEST = {
    104         'url': 'http://awaan.ae/live/6/dubai-tv',
    105         'info_dict': {
    106             'id': '6',
    107             'ext': 'mp4',
    108             'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
    109             'upload_date': '20150107',
    110             'timestamp': 1420588800,
    111             'uploader_id': '71',
    112         },
    113         'params': {
    114             # m3u8 download
    115             'skip_download': True,
    116         },
    117     }
    118 
    119     def _real_extract(self, url):
    120         channel_id = self._match_id(url)
    121 
    122         channel_data = self._download_json(
    123             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
    124             channel_id, headers={'Origin': 'http://awaan.ae'})
    125         info = self._parse_video_data(channel_data, channel_id, True)
    126 
    127         embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
    128             'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
    129             'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
    130             'signature': channel_data['signature'],
    131             'countries': 'Q0M=',
    132             'filter': 'DENY',
    133         })
    134         info.update({
    135             '_type': 'url_transparent',
    136             'url': embed_url,
    137             'ie_key': 'MangomoloLive',
    138         })
    139         return info
    140 
    141 
    142 class AWAANSeasonIE(InfoExtractor):
    143     IE_NAME = 'awaan:season'
    144     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
    145     _TEST = {
    146         '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',
    147         'info_dict':
    148         {
    149             'id': '7910',
    150             'title': 'محاضرات الشيخ الشعراوي',
    151         },
    152         'playlist_mincount': 27,
    153     }
    154 
    155     def _real_extract(self, url):
    156         url, smuggled_data = unsmuggle_url(url, {})
    157         show_id, season_id = re.match(self._VALID_URL, url).groups()
    158 
    159         data = {}
    160         if season_id:
    161             data['season'] = season_id
    162             show_id = smuggled_data.get('show_id')
    163             if show_id is None:
    164                 season = self._download_json(
    165                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
    166                     season_id, headers={'Origin': 'http://awaan.ae'})
    167                 show_id = season['id']
    168         data['show_id'] = show_id
    169         show = self._download_json(
    170             'http://admin.mangomolo.com/analytics/index.php/plus/show',
    171             show_id, data=urlencode_postdata(data), headers={
    172                 'Origin': 'http://awaan.ae',
    173                 'Content-Type': 'application/x-www-form-urlencoded'
    174             })
    175         if not season_id:
    176             season_id = show['default_season']
    177         for season in show['seasons']:
    178             if season['id'] == season_id:
    179                 title = season.get('title_en') or season['title_ar']
    180 
    181                 entries = []
    182                 for video in show['videos']:
    183                     video_id = compat_str(video['id'])
    184                     entries.append(self.url_result(
    185                         'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
    186 
    187                 return self.playlist_result(entries, season_id, title)