import re
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ ExtractorError,
+ unsmuggle_url,
+)
from ..compat import (
compat_parse_qs,
compat_urlparse,
["arch", "", "http://ussenate-f.akamaihd.net/"]
]
_IE_NAME = 'senate.gov'
- _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
+ _VALID_URL = r'http://www\.senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{
'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',
- 'md5': '7314c4b96dad66dd8e63dc3518ceaa6f',
'info_dict': {
'id': 'judiciary031715',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Integrated Senate Video Player',
- }
+ 'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
- 'md5': '2917c827513700aa9b70eaebf25116da',
'info_dict': {
'id': 'commerce011514',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Integrated Senate Video Player'
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
# checksum differs each time
'ext': 'mp4',
'title': 'Integrated Senate Video Player'
}
+ }, {
+ # From http://www.c-span.org/video/?96791-1
+ 'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
+ 'only_matching': True,
}]
+ @staticmethod
+ def _search_iframe_url(webpage):
+ mobj = re.search(
+ r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
+ webpage)
+ if mobj:
+ return mobj.group('url')
+
def _get_info_for_comm(self, committee):
for entry in self._COMM_MAP:
if entry[0] == committee:
return entry[1:]
def _real_extract(self, url):
+ url, smuggled_data = unsmuggle_url(url, {})
+
qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
raise ExtractorError('Invalid URL', expected=True)
webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
+ if smuggled_data.get('force_title'):
+ title = smuggled_data['force_title']
+ else:
+ title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
+ poster = qs.get('poster')
+ thumbnail = poster[0] if poster else None
video_type = qs['type'][0]
committee = video_type if video_type == 'arch' else qs['comm'][0]
'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
}]
else:
- hdcore_sign = '?hdcore=3.1.0'
+ hdcore_sign = 'hdcore=3.1.0'
url_params = (domain, video_id, stream_num)
- f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
+ f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
# URLs without the extra param induce an 404 error
self._sort_formats(formats)
- info_dict = {
+ return {
'id': video_id,
'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
}
-
- if len(formats) >= 1:
- info_dict.update({'formats': formats})
- else:
- info_dict.update(formats[0])
-
- return info_dict