MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-24 12:15:50 +01:00
Code Issues Projects Releases Wiki Activity

[extractor/common] add helper method to extract html5 media entries

Browse Source
This commit is contained in:
remitamine 2016-03-16 18:50:45 +01:00 committed by Remita Amine
parent 4f3c5e0627
commit 59bbe4911a
1 changed files with 58 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
youtube_dl/extractor/common.py
View File

@ -54,6 +54,8 @@
update_Request,
update_url_query,
parse_m3u8_attributes,
extract_attributes,
parse_codecs,
)
@ -1610,6 +1612,62 @@ def extract_multisegment_info(element, ms_parent_info):
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _parse_html5_media_entries(self, base_url, webpage):
def absolute_url(video_url):
return compat_urlparse.urljoin(base_url, video_url)
def parse_content_type(content_type):
if not content_type:
return {}
ctr = re.search(r'(?P<mimetype>[^/]+/[^;]+)(?:;\s*codecs="?(?P<codecs>[^"]+))?', content_type)
if ctr:
mimetype, codecs = ctr.groups()
f = parse_codecs(codecs)
f['ext'] = mimetype2ext(mimetype)
return f
return {}
entries = []
for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
media_info = {
'formats': [],
'subtitles': {},
}
media_attributes = extract_attributes(media_tag)
src = media_attributes.get('src')
if src:
media_info['formats'].append({
'url': absolute_url(src),
'vcodec': 'none' if media_type == 'audio' else None,
})
media_info['thumbnail'] = media_attributes.get('poster')
if media_content:
for source_tag in re.findall(r'<source[^>]+>', media_content):
source_attributes = extract_attributes(source_tag)
src = source_attributes.get('src')
if not src:
continue
f = parse_content_type(source_attributes.get('type'))
f.update({
'url': absolute_url(src),
'vcodec': 'none' if media_type == 'audio' else None,
})
media_info['formats'].append(f)
for track_tag in re.findall(r'<track[^>]+>', media_content):
track_attributes = extract_attributes(track_tag)
kind = track_attributes.get('kind')
if not kind or kind == 'subtitles':
src = track_attributes.get('src')
if not src:
continue
lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label')
media_info['subtitles'].setdefault(lang, []).append({
'url': absolute_url(src),
})
if media_info['formats']:
entries.append(media_info)
return entries
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()