2 from __future__ import unicode_literals
5 from .common import InfoExtractor
10 from ..compat import (
16 class SenateISVPIE(InfoExtractor):
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/"]
50 _IE_NAME = 'senate.gov'
51 _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
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',
55 'id': 'judiciary031715',
57 'title': 'Integrated Senate Video Player',
58 'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
61 'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
63 'id': 'commerce011514',
65 'title': 'Integrated Senate Video Player'
68 'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
69 # checksum differs each time
73 'title': 'Integrated Senate Video Player'
78 def _search_iframe_url(webpage):
80 r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
83 return mobj.group('url')
85 def _get_info_for_comm(self, committee):
86 for entry in self._COMM_MAP:
87 if entry[0] == committee:
90 def _real_extract(self, url):
91 url, smuggled_data = unsmuggle_url(url, {})
93 qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
94 if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
95 raise ExtractorError('Invalid URL', expected=True)
97 video_id = re.sub(r'.mp4$', '', qs['filename'][0])
99 webpage = self._download_webpage(url, video_id)
101 if smuggled_data.get('force_title'):
102 title = smuggled_data['force_title']
104 title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
105 poster = qs.get('poster')
106 thumbnail = poster[0] if poster else None
108 video_type = qs['type'][0]
109 committee = video_type if video_type == 'arch' else qs['comm'][0]
110 stream_num, domain = self._get_info_for_comm(committee)
113 if video_type == 'arch':
114 filename = video_id if '.' in video_id else video_id + '.mp4'
116 # All parameters in the query string are necessary to prevent a 403 error
117 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
120 hdcore_sign = '?hdcore=3.1.0'
121 url_params = (domain, video_id, stream_num)
122 f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
123 m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
124 for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
125 # URLs without the extra param induce an 404 error
126 entry.update({'extra_param_to_segment_url': hdcore_sign})
127 formats.append(entry)
128 for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
129 mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
131 entry['format_id'] += mobj.group('tag')
132 formats.append(entry)
134 self._sort_formats(formats)
140 'thumbnail': thumbnail,