pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-14 22:37:59 +09:00
Code Issues Projects Releases Wiki Activity

[discovery] extract more info using BrightcoveNewIE

Browse Source
This commit is contained in:
remitamine 2016-04-30 21:49:32 +01:00
parent 93f7a31bf3
commit d00b93d58c
1 changed files with 7 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/discovery.py
View File

@ -38,6 +38,7 @@ class DiscoveryIE(InfoExtractor):
'duration': 156, 'duration': 156,
'timestamp': 1302032462, 'timestamp': 1302032462,
'upload_date': '20110405', 'upload_date': '20110405',
'uploader_id': '103207',
}, },
'params': { 'params': {
'skip_download': True, # requires ffmpeg 'skip_download': True, # requires ffmpeg
@ -59,7 +60,11 @@ class DiscoveryIE(InfoExtractor):
'upload_date': '20140725', 'upload_date': '20140725',
'timestamp': 1406246400, 'timestamp': 1406246400,
'duration': 116, 'duration': 116,
'uploader_id': '103207',
}, },
'params': {
'skip_download': True, # requires ffmpeg
}
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -71,50 +76,6 @@ class DiscoveryIE(InfoExtractor):
entries = [] entries = []
for idx, video_info in enumerate(info['playlist']): for idx, video_info in enumerate(info['playlist']):
m3u8_url = video_info['src']
formats = m3u8_formats = self._extract_m3u8_formats(
m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls',
note='Download m3u8 information for video %d' % (idx + 1))
qualities_basename = self._search_regex(
'/([^/]+)\.csmil/', m3u8_url, 'qualities basename', default=None)
if qualities_basename:
m3u8_path = compat_urlparse.urlparse(m3u8_url).path
QUALITIES_RE = r'((,\d+k)+,?)'
qualities = self._search_regex(
QUALITIES_RE, qualities_basename,
'qualities', default=None)
if qualities:
qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(',')))
qualities.sort()
http_path = m3u8_path[1:].split('/', 1)[1]
http_template = re.sub(QUALITIES_RE, r'%dk', http_path)
http_template = http_template.replace('.csmil/master.m3u8', '')
http_template = compat_urlparse.urljoin(
'http://discsmil.edgesuite.net/', http_template)
if m3u8_formats:
self._sort_formats(m3u8_formats)
m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
m3u8_formats))
if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy()
f.update({
'url': http_template % q,
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
formats.append(f)
else:
for q in qualities:
formats.append({
'url': http_template % q,
'ext': 'mp4',
'format_id': 'http-%d' % q,
'tbr': q,
})
self._sort_formats(formats)
subtitles = [] subtitles = []
caption_url = video_info.get('captionsUrl') caption_url = video_info.get('captionsUrl')
if caption_url: if caption_url:
@ -125,8 +86,9 @@ class DiscoveryIE(InfoExtractor):
} }
entries.append({ entries.append({
'_type': 'url_transparent',
'url': 'http://players.brightcove.net/103207/default_default/index.html?videoId=ref:%s' % video_info['referenceId'],
'id': compat_str(video_info['id']), 'id': compat_str(video_info['id']),
'formats': formats,
'title': video_info['title'], 'title': video_info['title'],
'description': video_info.get('description'), 'description': video_info.get('description'),
'duration': parse_duration(video_info.get('video_length')), 'duration': parse_duration(video_info.get('video_length')),