_ 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/[^/]+/(?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/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
  14         'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
  15         'info_dict': {
  16             'id': '459911',
  17             'ext': 'mp4',
  18             'title': 'Organic mattresses used to clean waste water',
  19             'upload_date': '20160409',
  20             'thumbnail': 'http://media.presstv.com/photo/20160409/41719129-76fa-4372-a09d-bf348278eb5d.jpg',
  21             'description': ('A trial program at an Australian sewerage treatment facility hopes to change '
  22                             'the way waste water is treated by using plant mattresses to reduce chemical '
  23                             'and electricity use.')
  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].strip()
  62
  63         thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True)
  64         description = self._html_search_meta('og:description', webpage, 'Description', True)
  65
  66         year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y'))
  67         month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m'))
  68         day = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload day', group='d'))
  69         upload_date = '%04d%02d%02d' % (year, month, day)
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'formats': formats,
  75             'thumbnail': thumbnail,
  76             'upload_date': upload_date,
  77             'description': description
  78         }