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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import str_to_int
   7
   8
   9 class PressTVIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?presstv\.ir/Video/(?P<y>[0-9]+)/(?P<m>[0-9]+)/(?P<d>[0-9]+)/(?P<id>[0-9]+)/'
  11
  12     _TEST = {
  13         'url': 'http://www.presstv.ir/Video/2015/10/04/431915/Max-Igan-Press-TV-Face-to-Face',
  14         'md5': 'e95736ac75088b5f1e5bbb68f248f90d',
  15         'info_dict': {
  16             'id': '431915',
  17             'ext': 'mp4',
  18             'title': 'Press TV’s full interview with Max Igan',
  19             'upload_date': '20151004',
  20             'thumbnail': 'http://217.218.67.233/photo/20151004/d5c333ad-98f9-4bd3-bc3e-a1ad6a192803.jpg',
  21             'description': ('Watch Press TV’s full interview with Max Igan, a radio talk show host and political '
  22                             'commentator.\nThe interview, conducted on Press TV’s Face '
  23                             'to Face program, was aired on October 3, 2015.')
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         # extract video URL from webpage
  32         video_url = self._html_search_regex(r'<input type="hidden" id="inpPlayback" value="([^"]+)" />', webpage,
  33                                             'Video URL')
  34
  35         # build list of available formats
  36         # specified in http://www.presstv.ir/Scripts/playback.js
  37         base_url = 'http://192.99.219.222:82/presstv'
  38         formats = [
  39             {
  40                 'url': base_url + video_url,
  41                 'format': '1080p mp4',
  42                 'format_id': '1080p'
  43             }, {
  44                 'url': base_url + video_url.replace(".mp4", "_low800.mp4"),
  45                 'format': '720p mp4',
  46                 'format_id': '720p'
  47             }, {
  48                 'url': base_url + video_url.replace(".mp4", "_low400.mp4"),
  49                 'format': '360p mp4',
  50                 'format_id': '360p'
  51             }, {
  52                 'url': base_url + video_url.replace(".mp4", "_low200.mp4"),
  53                 'format': '180p mp4',
  54                 'format_id': '180p'
  55             }
  56         ]
  57         formats.reverse()
  58
  59         # extract video metadata
  60         title = self._html_search_meta('title', webpage, 'Title', True)
  61         title = title.partition(' - ')[2]
  62
  63         description = self._html_search_regex(r'<div class="media-text nano-content">(.*?)</div>', webpage,
  64                                               'Description', flags=re.DOTALL)
  65
  66         thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True)
  67
  68         year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y'))
  69         month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m'))
  70         day = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload day', group='d'))
  71         upload_date = '%04d%02d%02d' % (year, month, day)
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'formats': formats,
  77             'thumbnail': thumbnail,
  78             'upload_date': upload_date,
  79             'description': description
  80         }