[Senate] Add new extractor (#5302)

youtube_dl/downloader/f4m.py

@@ -389,6 +389,8 @@ class F4mFD(FileDownloader):
             url = base_url + name
             if akamai_pv:
                 url += '?' + akamai_pv.strip(';')
+            if info_dict.get('extra_param_to_segment_url'):
+                url += info_dict.get('extra_param_to_segment_url')
             frag_filename = '%s-%s' % (tmpfilename, name)
             try:
                 success = http_dl.download(frag_filename, {'url': url})

youtube_dl/extractor/__init__.py

@@ -447,6 +447,7 @@ from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
 from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
+from .senateisvp import SenateISVPIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE

youtube_dl/extractor/senateisvp.py

@@ -0,0 +1,129 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+from ..utils import ExtractorError
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
+
+
+class SenateISVPIE(InfoExtractor):
+    _COMM_MAP = [
+        ["ag", "76440", "http://ag-f.akamaihd.net"],
+        ["aging", "76442", "http://aging-f.akamaihd.net"],
+        ["approps", "76441", "http://approps-f.akamaihd.net"],
+        ["armed", "76445", "http://armed-f.akamaihd.net"],
+        ["banking", "76446", "http://banking-f.akamaihd.net"],
+        ["budget", "76447", "http://budget-f.akamaihd.net"],
+        ["cecc", "76486", "http://srs-f.akamaihd.net"],
+        ["commerce", "80177", "http://commerce1-f.akamaihd.net"],
+        ["csce", "75229", "http://srs-f.akamaihd.net"],
+        ["dpc", "76590", "http://dpc-f.akamaihd.net"],
+        ["energy", "76448", "http://energy-f.akamaihd.net"],
+        ["epw", "76478", "http://epw-f.akamaihd.net"],
+        ["ethics", "76449", "http://ethics-f.akamaihd.net"],
+        ["finance", "76450", "http://finance-f.akamaihd.net"],
+        ["foreign", "76451", "http://foreign-f.akamaihd.net"],
+        ["govtaff", "76453", "http://govtaff-f.akamaihd.net"],
+        ["help", "76452", "http://help-f.akamaihd.net"],
+        ["indian", "76455", "http://indian-f.akamaihd.net"],
+        ["intel", "76456", "http://intel-f.akamaihd.net"],
+        ["intlnarc", "76457", "http://intlnarc-f.akamaihd.net"],
+        ["jccic", "85180", "http://jccic-f.akamaihd.net"],
+        ["jec", "76458", "http://jec-f.akamaihd.net"],
+        ["judiciary", "76459", "http://judiciary-f.akamaihd.net"],
+        ["rpc", "76591", "http://rpc-f.akamaihd.net"],
+        ["rules", "76460", "http://rules-f.akamaihd.net"],
+        ["saa", "76489", "http://srs-f.akamaihd.net"],
+        ["smbiz", "76461", "http://smbiz-f.akamaihd.net"],
+        ["srs", "75229", "http://srs-f.akamaihd.net"],
+        ["uscc", "76487", "http://srs-f.akamaihd.net"],
+        ["vetaff", "76462", "http://vetaff-f.akamaihd.net"],
+        ["arch", "", "http://ussenate-f.akamaihd.net/"]
+    ]
+    _IE_NAME = 'senate.gov'
+    _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',
+            'title': 'Integrated Senate Video Player',
+        }
+    }, {
+        'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
+        'md5': '2917c827513700aa9b70eaebf25116da',
+        'info_dict': {
+            'id': 'commerce011514',
+            'ext': 'flv',
+            'title': 'Integrated Senate Video Player'
+        }
+    }, {
+        'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
+        # checksum differs each time
+        'info_dict': {
+            'id': 'intel090613',
+            'ext': 'mp4',
+            'title': 'Integrated Senate Video Player'
+        }
+    }]
+
+    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):
+        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)
+
+        video_id = re.sub(r'.mp4$', '', qs['filename'][0])
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
+
+        video_type = qs['type'][0]
+        committee = video_type if video_type == 'arch' else qs['comm'][0]
+        stream_num, domain = self._get_info_for_comm(committee)
+
+        formats = []
+        if video_type == 'arch':
+            filename = video_id if '.' in video_id else video_id + '.mp4'
+            formats = [{
+                # All parameters in the query string are necessary to prevent a 403 error
+                'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
+            }]
+        else:
+            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
+            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
+                entry.update({'extra_param_to_segment_url': hdcore_sign})
+                formats.append(entry)
+            for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
+                mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
+                if mobj:
+                    entry['format_id'] += mobj.group('tag')
+                formats.append(entry)
+
+            self._sort_formats(formats)
+
+        info_dict = {
+            'id': video_id,
+            'title': title,
+        }
+
+        if len(formats) >= 1:
+            info_dict.update({'formats': formats})
+        else:
+            info_dict.update(formats[0])
+
+        return info_dict