Add support for https for all extractors as preventive and future-proof measure

[youtube-dl] / youtube_dl / extractor / cspan.py

diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index 388460a324e8c7a03a2146ec0917996948c0dccc..84b36f44cfac7bd45a8a7d28adb6767093a7d19b 100644 (file)
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -15,7 +15,7 @@ from .senateisvp import SenateISVPIE
 
 
 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',
@@ -56,29 +56,39 @@ class CSpanIE(InfoExtractor):
         }
     }]
 
-    def get_text_attr(self, d, attr):
-        return d.get(attr, {}).get('#text')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        video_type = None
         webpage = self._download_webpage(url, video_id)
-        matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
-        if matches:
+        # 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)))
+        if results:
+            matches = results[0]
             video_type, video_id = matches.groups()
-            if video_type == 'prog':
-                video_type = 'program'
+            video_type = 'clip' if video_type == 'id' else 'program'
         else:
-            senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
-            if senate_isvp_url:
-                title = self._og_search_title(webpage)
-                surl = smuggle_url(senate_isvp_url, {'force_title': title})
-                return self.url_result(surl, 'SenateISVP', video_id, title)
+            m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage)
+            if m:
+                video_id = m.group('id')
+                video_type = 'program' if m.group('type') == 'prog' else 'clip'
+            else:
+                senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+                if senate_isvp_url:
+                    title = self._og_search_title(webpage)
+                    surl = smuggle_url(senate_isvp_url, {'force_title': title})
+                    return self.url_result(surl, 'SenateISVP', video_id, title)
+        if video_type is None or video_id is None:
+            raise ExtractorError('unable to find video id and type')
+
+        def get_text_attr(d, attr):
+            return d.get(attr, {}).get('#text')
 
         data = self._download_json(
             'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
             video_id)['video']
         if data['@status'] != 'Success':
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, self.get_text_attr(data, 'error')), expected=True)
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
 
         doc = self._download_xml(
             'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
@@ -90,18 +100,25 @@ class CSpanIE(InfoExtractor):
         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
 
         files = data['files']
-        capfile = self.get_text_attr(data, 'capfile')
+        capfile = get_text_attr(data, 'capfile')
 
         entries = []
         for partnum, f in enumerate(files):
             formats = []
             for quality in f['qualities']:
                 formats.append({
-                    'format_id': '%s-%sp' % (self.get_text_attr(quality, 'bitrate'), self.get_text_attr(quality, 'height')),
-                    'url': unescapeHTML(self.get_text_attr(quality, 'file')),
-                    'height': int_or_none(self.get_text_attr(quality, 'height')),
-                    'tbr': int_or_none(self.get_text_attr(quality, 'bitrate')),
+                    'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
+                    'url': unescapeHTML(get_text_attr(quality, 'file')),
+                    'height': int_or_none(get_text_attr(quality, 'height')),
+                    'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
                 })
+            if not formats:
+                path = unescapeHTML(get_text_attr(f, 'path'))
+                if not path:
+                    continue
+                formats = self._extract_m3u8_formats(
+                    path, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
             self._sort_formats(formats)
             entries.append({
                 'id': '%s_%d' % (video_id, partnum + 1),
@@ -111,7 +128,7 @@ class CSpanIE(InfoExtractor):
                 'formats': formats,
                 'description': description,
                 'thumbnail': thumbnail,
-                'duration': int_or_none(self.get_text_attr(f, 'length')),
+                'duration': int_or_none(get_text_attr(f, 'length')),
                 'subtitles': {
                     'en': [{
                         'url': capfile,