Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nick.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .mtv import MTVServicesInfoExtractor
   7 from ..utils import update_url_query
   8
   9
  10 class NickIE(MTVServicesInfoExtractor):
  11     # None of videos on the website are still alive?
  12     IE_NAME = 'nick.com'
  13     _VALID_URL = r'https?://(?:(?:www|beta)\.)?nick(?:jr)?\.com/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
  14     _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
  15     _TESTS = [{
  16         'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
  17         'playlist': [
  18             {
  19                 'md5': '6e5adc1e28253bbb1b28ab05403dd4d4',
  20                 'info_dict': {
  21                     'id': 'be6a17b0-412d-11e5-8ff7-0026b9414f30',
  22                     'ext': 'mp4',
  23                     'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S1',
  24                     'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
  25
  26                 }
  27             },
  28             {
  29                 'md5': 'd7be441fc53a1d4882fa9508a1e5b3ce',
  30                 'info_dict': {
  31                     'id': 'be6b8f96-412d-11e5-8ff7-0026b9414f30',
  32                     'ext': 'mp4',
  33                     'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S2',
  34                     'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
  35
  36                 }
  37             },
  38             {
  39                 'md5': 'efffe1728a234b2b0d2f2b343dd1946f',
  40                 'info_dict': {
  41                     'id': 'be6cf7e6-412d-11e5-8ff7-0026b9414f30',
  42                     'ext': 'mp4',
  43                     'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S3',
  44                     'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
  45                 }
  46             },
  47             {
  48                 'md5': '1ec6690733ab9f41709e274a1d5c7556',
  49                 'info_dict': {
  50                     'id': 'be6e3354-412d-11e5-8ff7-0026b9414f30',
  51                     'ext': 'mp4',
  52                     'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S4',
  53                     'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
  54                 }
  55             },
  56         ],
  57     }, {
  58         'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/',
  59         'only_matching': True,
  60     }, {
  61         'url': 'http://beta.nick.com/nicky-ricky-dicky-and-dawn/videos/nicky-ricky-dicky-dawn-301-full-episode/',
  62         'only_matching': True,
  63     }]
  64
  65     def _get_feed_query(self, uri):
  66         return {
  67             'feed': 'nick_arc_player_prime',
  68             'mgid': uri,
  69         }
  70
  71     def _extract_mgid(self, webpage):
  72         return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid')
  73
  74
  75 class NickDeIE(MTVServicesInfoExtractor):
  76     IE_NAME = 'nick.de'
  77     _VALID_URL = r'https?://(?:www\.)?(?P<host>nick\.de|nickelodeon\.(?:nl|at))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  78     _TESTS = [{
  79         'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
  80         'only_matching': True,
  81     }, {
  82         'url': 'http://www.nick.de/shows/342-icarly',
  83         'only_matching': True,
  84     }, {
  85         'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit',
  86         'only_matching': True,
  87     }, {
  88         'url': 'http://www.nickelodeon.at/playlist/3773-top-videos/videos/episode/77993-das-letzte-gefecht',
  89         'only_matching': True,
  90     }]
  91
  92     def _extract_mrss_url(self, webpage, host):
  93         return update_url_query(self._search_regex(
  94             r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'),
  95             {'siteKey': host})
  96
  97     def _real_extract(self, url):
  98         mobj = re.match(self._VALID_URL, url)
  99         video_id = mobj.group('id')
 100         host = mobj.group('host')
 101
 102         webpage = self._download_webpage(url, video_id)
 103
 104         mrss_url = self._extract_mrss_url(webpage, host)
 105
 106         return self._get_videos_info_from_url(mrss_url, video_id)
 107
 108
 109 class NickNightIE(NickDeIE):
 110     IE_NAME = 'nicknight'
 111     _VALID_URL = r'https?://(?:www\.)(?P<host>nicknight\.(?:de|at|tv))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 112     _TESTS = [{
 113         'url': 'http://www.nicknight.at/shows/977-awkward/videos/85987-nimmer-beste-freunde',
 114         'only_matching': True,
 115     }, {
 116         'url': 'http://www.nicknight.at/shows/977-awkward',
 117         'only_matching': True,
 118     }, {
 119         'url': 'http://www.nicknight.at/shows/1900-faking-it',
 120         'only_matching': True,
 121     }]
 122
 123     def _extract_mrss_url(self, webpage, *args):
 124         return self._search_regex(
 125             r'mrss\s*:\s*(["\'])(?P<url>http.+?)\1', webpage,
 126             'mrss url', group='url')