New upstream version 2019.01.16

[youtubedl] / youtube_dl / extractor / cspan.py

diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index b8b9d058ddce866fa497597863c80d1de0a7f5c5..67d6df4b0eb285f588b1352eae4a46e0c4b220fd 100644 (file)
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -4,32 +4,34 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    int_or_none,
-    unescapeHTML,
-    find_xpath_attr,
-    smuggle_url,

     determine_ext,
     ExtractorError,
     determine_ext,
     ExtractorError,

+    extract_attributes,
+    find_xpath_attr,
+    get_element_by_class,
+    int_or_none,
+    smuggle_url,
+    unescapeHTML,

 )
 from .senateisvp import SenateISVPIE
 )
 from .senateisvp import SenateISVPIE

+from .ustream import UstreamIE

 
 
 class CSpanIE(InfoExtractor):
 
 
 class CSpanIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'

     IE_DESC = 'C-SPAN'
     _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
         'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',
     IE_DESC = 'C-SPAN'
     _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
         'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',

-            'ext': 'mp4',

             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',

-            'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',

         },
         },

+        'playlist_mincount': 2,

         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',

-        'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
+        # md5 is unstable

         'info_dict': {
             'id': 'c4486943',
             'ext': 'mp4',
         'info_dict': {
             'id': 'c4486943',
             'ext': 'mp4',


@@ -38,28 +40,64 @@ class CSpanIE(InfoExtractor):
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',

-        'md5': '2ae5051559169baadba13fc35345ae74',

         'info_dict': {
             'id': '342759',
         'info_dict': {
             'id': '342759',

-            'ext': 'mp4',

             'title': 'General Motors Ignition Switch Recall',
             'title': 'General Motors Ignition Switch Recall',

-            'duration': 14848,
-            'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'

         },
         },

+        'playlist_mincount': 6,

     }, {
         # Video from senate.gov
         'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
         'info_dict': {
             'id': 'judiciary031715',
     }, {
         # Video from senate.gov
         'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
         'info_dict': {
             'id': 'judiciary031715',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
             'title': 'Immigration Reforms Needed to Protect Skilled American Workers',

+        },
+        'params': {
+            'skip_download': True,  # m3u8 downloads

         }
         }

+    }, {
+        # Ustream embedded video
+        'url': 'https://www.c-span.org/video/?114917-1/armed-services',
+        'info_dict': {
+            'id': '58428542',
+            'ext': 'flv',
+            'title': 'USHR07 Armed Services Committee',
+            'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
+            'timestamp': 1423060374,
+            'upload_date': '20150204',
+            '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)
         video_type = None
         webpage = self._download_webpage(url, video_id)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_type = None
         webpage = self._download_webpage(url, video_id)

+
+        ustream_url = UstreamIE._extract_url(webpage)
+        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}))
+

         # 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)))
         # 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)))


@@ -78,7 +116,15 @@ 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)
                     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:
         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):
             raise ExtractorError('unable to find video id and type')
 
         def get_text_attr(d, attr):


@@ -105,7 +151,7 @@ class CSpanIE(InfoExtractor):
         entries = []
         for partnum, f in enumerate(files):
             formats = []
         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')),
                 formats.append({
                     'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
                     'url': unescapeHTML(get_text_attr(quality, 'file')),