X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcspan.py;h=2e01aff488f00609744b5c16ba757fdcf0a193d2;hb=e13a01061d149f4fac7db1a50124c4745a11c16e;hp=d4576160b4489e599e4ca7dabc1e18c9d685610f;hpb=f3c21cb7a7e2d8685f466368e3142739077498cf;p=youtube-dl.git

diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index d4576160b4..2e01aff488 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -4,12 +4,19 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    int_or_none,
-    unescapeHTML,
-    find_xpath_attr,
-    smuggle_url,
     determine_ext,
     ExtractorError,
+    extract_attributes,
+    find_xpath_attr,
+    get_element_by_attribute,
+    get_element_by_class,
+    int_or_none,
+    js_to_json,
+    merge_dicts,
+    parse_iso8601,
+    smuggle_url,
+    str_to_int,
+    unescapeHTML,
 )
 from .senateisvp import SenateISVPIE
 from .ustream import UstreamIE
@@ -67,7 +74,12 @@ class CSpanIE(InfoExtractor):
             'uploader': 'HouseCommittee',
             'uploader_id': '12987475',
         },
+    }, {
+        # Audio Only
+        'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights',
+        'only_matching': True,
     }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -78,6 +90,61 @@ class CSpanIE(InfoExtractor):
         if ustream_url:
             return self.url_result(ustream_url, UstreamIE.ie_key())
 
+        if '&vod' not in url:
+            bc = self._search_regex(
+                r"(<[^>]+id='brightcove-player-embed'[^>]+>)",
+                webpage, 'brightcove embed', default=None)
+            if bc:
+                bc_attr = extract_attributes(bc)
+                bc_url = self.BRIGHTCOVE_URL_TEMPLATE % (
+                    bc_attr.get('data-bcaccountid', '3162030207001'),
+                    bc_attr.get('data-noprebcplayerid', 'SyGGpuJy3g'),
+                    bc_attr.get('data-newbcplayerid', 'default'),
+                    bc_attr['data-bcid'])
+                return self.url_result(smuggle_url(bc_url, {'source_url': url}))
+
+        def add_referer(formats):
+            for f in formats:
+                f.setdefault('http_headers', {})['Referer'] = url
+
+        # As of 01.12.2020 this path looks to cover all cases making the rest
+        # of the code unnecessary
+        jwsetup = self._parse_json(
+            self._search_regex(
+                r'(?s)jwsetup\s*=\s*({.+?})\s*;', webpage, 'jwsetup',
+                default='{}'),
+            video_id, transform_source=js_to_json, fatal=False)
+        if jwsetup:
+            info = self._parse_jwplayer_data(
+                jwsetup, video_id, require_title=False, m3u8_id='hls',
+                base_url=url)
+            add_referer(info['formats'])
+            for subtitles in info['subtitles'].values():
+                for subtitle in subtitles:
+                    ext = determine_ext(subtitle['url'])
+                    if ext == 'php':
+                        ext = 'vtt'
+                    subtitle['ext'] = ext
+            ld_info = self._search_json_ld(webpage, video_id, default={})
+            title = get_element_by_class('video-page-title', webpage) or \
+                self._og_search_title(webpage)
+            description = get_element_by_attribute('itemprop', 'description', webpage) or \
+                self._html_search_meta(['og:description', 'description'], webpage)
+            return merge_dicts(info, ld_info, {
+                'title': title,
+                'thumbnail': get_element_by_attribute('itemprop', 'thumbnailUrl', webpage),
+                'description': description,
+                'timestamp': parse_iso8601(get_element_by_attribute('itemprop', 'uploadDate', webpage)),
+                'location': get_element_by_attribute('itemprop', 'contentLocation', webpage),
+                'duration': int_or_none(self._search_regex(
+                    r'jwsetup\.seclength\s*=\s*(\d+);',
+                    webpage, 'duration', fatal=False)),
+                'view_count': str_to_int(self._search_regex(
+                    r"<span[^>]+class='views'[^>]*>([\d,]+)\s+Views</span>",
+                    webpage, 'views', fatal=False)),
+            })
+
+        # Obsolete
         # We first look for clipid, because clipprog always appears before
         patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
         results = list(filter(None, (re.search(p, webpage) for p in patterns)))
@@ -96,7 +163,15 @@ class CSpanIE(InfoExtractor):
                     title = self._og_search_title(webpage)
                     surl = smuggle_url(senate_isvp_url, {'force_title': title})
                     return self.url_result(surl, 'SenateISVP', video_id, title)
+                video_id = self._search_regex(
+                    r'jwsetup\.clipprog\s*=\s*(\d+);',
+                    webpage, 'jwsetup program id', default=None)
+                if video_id:
+                    video_type = 'program'
         if video_type is None or video_id is None:
+            error_message = get_element_by_class('VLplayer-error-message', webpage)
+            if error_message:
+                raise ExtractorError(error_message)
             raise ExtractorError('unable to find video id and type')
 
         def get_text_attr(d, attr):
@@ -123,7 +198,7 @@ class CSpanIE(InfoExtractor):
         entries = []
         for partnum, f in enumerate(files):
             formats = []
-            for quality in f['qualities']:
+            for quality in f.get('qualities', []):
                 formats.append({
                     'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
                     'url': unescapeHTML(get_text_attr(quality, 'file')),
@@ -137,6 +212,7 @@ class CSpanIE(InfoExtractor):
                 formats = self._extract_m3u8_formats(
                     path, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
+            add_referer(formats)
             self._sort_formats(formats)
             entries.append({
                 'id': '%s_%d' % (video_id, partnum + 1),