_ Git - youtube-dl/blob - youtube_dl/extractor/moevideo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  15 )
  16
  17
  18 class MoeVideoIE(InfoExtractor):
  19     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
  20     _VALID_URL = r'''(?x)
  21         https?://(?P<host>(?:www\.)?
  22         (?:(?:moevideo|playreplay|videochart)\.net))/
  23         (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)'''
  24     _API_URL = 'http://api.letitbit.net/'
  25     _API_KEY = 'tVL0gjqo5'
  26     _TESTS = [
  27         {
  28             'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
  29             'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
  30             'info_dict': {
  31                 'id': '00297.0036103fe3d513ef27915216fd29',
  32                 'ext': 'flv',
  33                 'title': 'Sink cut out machine',
  34                 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
  35                 'thumbnail': 're:^https?://.*\.jpg$',
  36                 'width': 540,
  37                 'height': 360,
  38                 'duration': 179,
  39                 'filesize': 17822500,
  40             }
  41         },
  42         {
  43             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
  44             'md5': '74f0a014d5b661f0f0e2361300d1620e',
  45             'info_dict': {
  46                 'id': '77107.7f325710a627383d40540d8e991a',
  47                 'ext': 'flv',
  48                 'title': 'Operacion Condor.',
  49                 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
  50                 'thumbnail': 're:^https?://.*\.jpg$',
  51                 'width': 480,
  52                 'height': 296,
  53                 'duration': 6027,
  54                 'filesize': 588257923,
  55             },
  56             'skip': 'Video has been removed',
  57         },
  58     ]
  59
  60     def _real_extract(self, url):
  61         mobj = re.match(self._VALID_URL, url)
  62         video_id = mobj.group('id')
  63
  64         webpage = self._download_webpage(
  65             'http://%s/video/%s' % (mobj.group('host'), video_id),
  66             video_id, 'Downloading webpage')
  67
  68         title = self._og_search_title(webpage)
  69         thumbnail = self._og_search_thumbnail(webpage)
  70         description = self._og_search_description(webpage)
  71
  72         r = [
  73             self._API_KEY,
  74             [
  75                 'preview/flv_link',
  76                 {
  77                     'uid': video_id,
  78                 },
  79             ],
  80         ]
  81         r_json = json.dumps(r)
  82         post = compat_urllib_parse.urlencode({'r': r_json})
  83         req = compat_urllib_request.Request(self._API_URL, post)
  84         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  85
  86         response = self._download_json(req, video_id)
  87         if response['status'] != 'OK':
  88             raise ExtractorError(
  89                 '%s returned error: %s' % (self.IE_NAME, response['data']),
  90                 expected=True
  91             )
  92         item = response['data'][0]
  93         video_url = item['link']
  94         duration = int_or_none(item['length'])
  95         width = int_or_none(item['width'])
  96         height = int_or_none(item['height'])
  97         filesize = int_or_none(item['convert_size'])
  98
  99         formats = [{
 100             'format_id': 'sd',
 101             'http_headers': {'Range': 'bytes=0-'},  # Required to download
 102             'url': video_url,
 103             'width': width,
 104             'height': height,
 105             'filesize': filesize,
 106         }]
 107
 108         return {
 109             'id': video_id,
 110             'title': title,
 111             'thumbnail': thumbnail,
 112             'description': description,
 113             'duration': duration,
 114             'formats': formats,
 115         }