Merge branch 'douyutv' of https://github.com/bonfy/youtube-dl into bonfy-douyutv

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

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 4fe99d25de7d615aeca56a1f9608e5053a77d522..e5245ec3f29eb914b4a311bdf5f3c735e32d2f61 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -767,6 +767,10 @@ class InfoExtractor(object):
                 formats)
 
     def _is_valid_url(self, url, video_id, item='video'):
+        url = self._proto_relative_url(url, scheme='http:')
+        # For now assume non HTTP(S) URLs always valid
+        if not (url.startswith('http://') or url.startswith('https://')):
+            return True
         try:
             self._request_webpage(url, video_id, 'Checking %s URL' % item)
             return True
@@ -835,7 +839,7 @@ class InfoExtractor(object):
                               m3u8_id=None):
 
         formats = [{
-            'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
+            'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
@@ -879,8 +883,13 @@ class InfoExtractor(object):
                     formats.append({'url': format_url(line)})
                     continue
                 tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+                format_id = []
+                if m3u8_id:
+                    format_id.append(m3u8_id)
+                last_media_name = last_media.get('NAME') if last_media else None
+                format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
                 f = {
-                    'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
+                    'format_id': '-'.join(format_id),
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
@@ -923,18 +932,18 @@ class InfoExtractor(object):
         rtmp_count = 0
         if smil.findall('./body/seq/video'):
             video = smil.findall('./body/seq/video')[0]
-            fmts, rtmp_count = self._parse_smil_video(video, base, rtmp_count)
+            fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
             formats.extend(fmts)
         else:
             for video in smil.findall('./body/switch/video'):
-                fmts, rtmp_count = self._parse_smil_video(video, base, rtmp_count)
+                fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
                 formats.extend(fmts)
 
         self._sort_formats(formats)
 
         return formats
 
-    def _parse_smil_video(self, video, base, rtmp_count):
+    def _parse_smil_video(self, video, video_id, base, rtmp_count):
         src = video.get('src')
         if not src:
             return ([], rtmp_count)
@@ -963,6 +972,14 @@ class InfoExtractor(object):
                 'width': width,
                 'height': height,
             }], rtmp_count)
+        elif proto.startswith('http'):
+            return ([{
+                'url': base + src,
+                'ext': ext or 'flv',
+                'tbr': bitrate,
+                'width': width,
+                'height': height,
+            }], rtmp_count)
 
     def _live_title(self, name):
         """ Generate the title for a live video """
@@ -1045,6 +1062,9 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
+    def _subtitles_timecode(self, seconds):
+        return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """