etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
Code Issues Projects Releases Wiki Activity

[youtube] improve m3u8 format extraction

Browse source
This commit is contained in:
Remita Amine 2017-04-11 21:55:59 +01:00
parent e109f1ff43
commit 89beedd31f
1 changed files with 15 additions and 32 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
youtube_dl/extractor/youtube.py
View file

@ -1253,21 +1253,6 @@ def extract_id(cls, url):
video_id = mobj.group(2) video_id = mobj.group(2)
return video_id return video_id
def _extract_from_m3u8(self, manifest_url, video_id):
url_map = {}
def _get_urls(_manifest):
lines = _manifest.split('\n')
urls = filter(lambda l: l and not l.startswith('#'),
lines)
return urls
manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
formats_urls = _get_urls(manifest)
for format_url in formats_urls:
itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
url_map[itag] = format_url
return url_map
def _extract_annotations(self, video_id): def _extract_annotations(self, video_id):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
@ -1573,19 +1558,6 @@ def _extract_count(count_name):
if self._downloader.params.get('writeannotations', False): if self._downloader.params.get('writeannotations', False):
video_annotations = self._extract_annotations(video_id) video_annotations = self._extract_annotations(video_id)
def _map_to_format_list(urlmap):
formats = []
for itag, video_real_url in urlmap.items():
dct = {
'format_id': itag,
'url': video_real_url,
'player_url': player_url,
}
if itag in self._formats:
dct.update(self._formats[itag])
formats.append(dct)
return formats
if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download() self.report_rtmp_download()
formats = [{ formats = [{
@ -1718,11 +1690,22 @@ def _map_to_format_list(urlmap):
formats.append(dct) formats.append(dct)
elif video_info.get('hlsvp'): elif video_info.get('hlsvp'):
manifest_url = video_info['hlsvp'][0] manifest_url = video_info['hlsvp'][0]
url_map = self._extract_from_m3u8(manifest_url, video_id) formats = []
formats = _map_to_format_list(url_map) m3u8_formats = self._extract_m3u8_formats(
# Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming manifest_url, video_id, 'mp4', fatal=False)
for a_format in formats: for a_format in m3u8_formats:
itag = self._search_regex(
r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
if itag:
a_format['format_id'] = itag
if itag in self._formats:
dct = self._formats[itag].copy()
dct.update(a_format)
a_format = dct
a_format['player_url'] = player_url
# Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
formats.append(a_format)
else: else:
unavailable_message = self._html_search_regex( unavailable_message = self._html_search_regex(
r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>', r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',