Merge pull request #8876 from remitamine/html5_media

[extractor/common] add helper method to extract html5 media entries
This commit is contained in:
Yen Chi Hsuan 2016-07-10 23:40:45 +08:00 committed by GitHub
commit 0b68de3cc1
3 changed files with 118 additions and 0 deletions

View File

@ -81,6 +81,7 @@
cli_option,
cli_valueless_option,
cli_bool_option,
parse_codecs,
)
from youtube_dl.compat import (
compat_chr,
@ -608,6 +609,29 @@ def test_limit_length(self):
limit_length('foo bar baz asd', 12).startswith('foo bar'))
self.assertTrue('...' in limit_length('foo bar baz asd', 12))
def test_parse_codecs(self):
self.assertEqual(parse_codecs(''), {})
self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
'vcodec': 'avc1.77.30',
'acodec': 'mp4a.40.2',
})
self.assertEqual(parse_codecs('mp4a.40.2'), {
'vcodec': 'none',
'acodec': 'mp4a.40.2',
})
self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
'vcodec': 'avc1.42001e',
'acodec': 'mp4a.40.5',
})
self.assertEqual(parse_codecs('avc3.640028'), {
'vcodec': 'avc3.640028',
'acodec': 'none',
})
self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
'vcodec': 'h264',
'acodec': 'aac',
})
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"
unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'

View File

@ -55,6 +55,8 @@
update_Request,
update_url_query,
parse_m3u8_attributes,
extract_attributes,
parse_codecs,
)
@ -1635,6 +1637,62 @@ 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()

View File

@ -2126,6 +2126,42 @@ def mimetype2ext(mt):
}.get(res, res)
def parse_codecs(codecs_str):
# http://tools.ietf.org/html/rfc6381
if not codecs_str:
return {}
splited_codecs = list(filter(None, map(
lambda str: str.strip(), codecs_str.strip().strip(',').split(','))))
vcodec, acodec = None, None
for full_codec in splited_codecs:
codec = full_codec.split('.')[0]
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v'):
if not vcodec:
vcodec = full_codec
elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac'):
if not acodec:
acodec = full_codec
else:
write_string('WARNING: Unknown codec %s' % full_codec, sys.stderr)
if not vcodec and not acodec:
if len(splited_codecs) == 2:
return {
'vcodec': vcodec,
'acodec': acodec,
}
elif len(splited_codecs) == 1:
return {
'vcodec': 'none',
'acodec': vcodec,
}
else:
return {
'vcodec': vcodec or 'none',
'acodec': acodec or 'none',
}
return {}
def urlhandle_detect_ext(url_handle):
getheader = url_handle.headers.get