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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     unsmuggle_url,
   9 )
  10 from ..compat import (
  11     compat_parse_qs,
  12     compat_urlparse,
  13 )
  14
  15
  16 class SenateISVPIE(InfoExtractor):
  17     _COMM_MAP = [
  18         ['ag', '76440', 'http://ag-f.akamaihd.net'],
  19         ['aging', '76442', 'http://aging-f.akamaihd.net'],
  20         ['approps', '76441', 'http://approps-f.akamaihd.net'],
  21         ['armed', '76445', 'http://armed-f.akamaihd.net'],
  22         ['banking', '76446', 'http://banking-f.akamaihd.net'],
  23         ['budget', '76447', 'http://budget-f.akamaihd.net'],
  24         ['cecc', '76486', 'http://srs-f.akamaihd.net'],
  25         ['commerce', '80177', 'http://commerce1-f.akamaihd.net'],
  26         ['csce', '75229', 'http://srs-f.akamaihd.net'],
  27         ['dpc', '76590', 'http://dpc-f.akamaihd.net'],
  28         ['energy', '76448', 'http://energy-f.akamaihd.net'],
  29         ['epw', '76478', 'http://epw-f.akamaihd.net'],
  30         ['ethics', '76449', 'http://ethics-f.akamaihd.net'],
  31         ['finance', '76450', 'http://finance-f.akamaihd.net'],
  32         ['foreign', '76451', 'http://foreign-f.akamaihd.net'],
  33         ['govtaff', '76453', 'http://govtaff-f.akamaihd.net'],
  34         ['help', '76452', 'http://help-f.akamaihd.net'],
  35         ['indian', '76455', 'http://indian-f.akamaihd.net'],
  36         ['intel', '76456', 'http://intel-f.akamaihd.net'],
  37         ['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net'],
  38         ['jccic', '85180', 'http://jccic-f.akamaihd.net'],
  39         ['jec', '76458', 'http://jec-f.akamaihd.net'],
  40         ['judiciary', '76459', 'http://judiciary-f.akamaihd.net'],
  41         ['rpc', '76591', 'http://rpc-f.akamaihd.net'],
  42         ['rules', '76460', 'http://rules-f.akamaihd.net'],
  43         ['saa', '76489', 'http://srs-f.akamaihd.net'],
  44         ['smbiz', '76461', 'http://smbiz-f.akamaihd.net'],
  45         ['srs', '75229', 'http://srs-f.akamaihd.net'],
  46         ['uscc', '76487', 'http://srs-f.akamaihd.net'],
  47         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
  48         ['arch', '', 'http://ussenate-f.akamaihd.net/']
  49     ]
  50     _IE_NAME = 'senate.gov'
  51     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
  52     _TESTS = [{
  53         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
  54         'info_dict': {
  55             'id': 'judiciary031715',
  56             'ext': 'mp4',
  57             'title': 'Integrated Senate Video Player',
  58             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
  59         },
  60         'params': {
  61             # m3u8 download
  62             'skip_download': True,
  63         },
  64     }, {
  65         'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
  66         'info_dict': {
  67             'id': 'commerce011514',
  68             'ext': 'mp4',
  69             'title': 'Integrated Senate Video Player'
  70         },
  71         'params': {
  72             # m3u8 download
  73             'skip_download': True,
  74         },
  75     }, {
  76         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
  77         # checksum differs each time
  78         'info_dict': {
  79             'id': 'intel090613',
  80             'ext': 'mp4',
  81             'title': 'Integrated Senate Video Player'
  82         }
  83     }, {
  84         # From http://www.c-span.org/video/?96791-1
  85         'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
  86         'only_matching': True,
  87     }]
  88
  89     @staticmethod
  90     def _search_iframe_url(webpage):
  91         mobj = re.search(
  92             r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
  93             webpage)
  94         if mobj:
  95             return mobj.group('url')
  96
  97     def _get_info_for_comm(self, committee):
  98         for entry in self._COMM_MAP:
  99             if entry[0] == committee:
 100                 return entry[1:]
 101
 102     def _real_extract(self, url):
 103         url, smuggled_data = unsmuggle_url(url, {})
 104
 105         qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
 106         if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
 107             raise ExtractorError('Invalid URL', expected=True)
 108
 109         video_id = re.sub(r'.mp4$', '', qs['filename'][0])
 110
 111         webpage = self._download_webpage(url, video_id)
 112
 113         if smuggled_data.get('force_title'):
 114             title = smuggled_data['force_title']
 115         else:
 116             title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
 117         poster = qs.get('poster')
 118         thumbnail = poster[0] if poster else None
 119
 120         video_type = qs['type'][0]
 121         committee = video_type if video_type == 'arch' else qs['comm'][0]
 122         stream_num, domain = self._get_info_for_comm(committee)
 123
 124         formats = []
 125         if video_type == 'arch':
 126             filename = video_id if '.' in video_id else video_id + '.mp4'
 127             formats = [{
 128                 # All parameters in the query string are necessary to prevent a 403 error
 129                 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
 130             }]
 131         else:
 132             hdcore_sign = 'hdcore=3.1.0'
 133             url_params = (domain, video_id, stream_num)
 134             f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
 135             m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
 136             for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
 137                 # URLs without the extra param induce an 404 error
 138                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 139                 formats.append(entry)
 140             for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
 141                 mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
 142                 if mobj:
 143                     entry['format_id'] += mobj.group('tag')
 144                 formats.append(entry)
 145
 146             self._sort_formats(formats)
 147
 148         return {
 149             'id': video_id,
 150             'title': title,
 151             'formats': formats,
 152             'thumbnail': thumbnail,
 153         }