Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-08 04:02:40 +01:00
Code Issues Releases Activity

[discovery] extract http formats

Browse Source
This commit is contained in:
remitamine 2016-04-30 20:38:45 +01:00
parent 4e0c0c1508
commit 33a1ec950c
1 changed files with 47 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
youtube_dl/extractor/discovery.py
View File

@ -1,11 +1,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
) )
from ..compat import compat_str from ..compat import (
compat_str,
compat_urlparse,
)
class DiscoveryIE(InfoExtractor): class DiscoveryIE(InfoExtractor):
@ -66,9 +71,48 @@ def _real_extract(self, url):
entries = [] entries = []
for idx, video_info in enumerate(info['playlist']): for idx, video_info in enumerate(info['playlist']):
formats = self._extract_m3u8_formats( m3u8_url = video_info['src']
video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls', 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)) 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) self._sort_formats(formats)
entries.append({ entries.append({
'id': compat_str(video_info['id']), 'id': compat_str(video_info['id']),