mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 22:29:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

[sixplay] improve extraction

Browse source 
- skip drm protected formats
- extract more and better formats
- skip duplicate asset urls
This commit is contained in:
Remita Amine 2017-02-08 22:56:10 +01:00
parent 8298018273
commit c8b8fb0a99
1 changed files with 25 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
youtube_dl/extractor/sixplay.py
View file

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import (
@ -12,6 +14,7 @@
class SixPlayIE(InfoExtractor): class SixPlayIE(InfoExtractor):
IE_NAME = '6play'
_VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)' _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'
_TEST = { _TEST = {
'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450', 'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450',
@ -42,21 +45,36 @@ def _real_extract(self, url):
clip_data = data['clips'][0] clip_data = data['clips'][0]
title = clip_data['title'] title = clip_data['title']
urls = []
quality_key = qualities(['lq', 'sd', 'hq', 'hd']) quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
formats = [] formats = []
for asset in clip_data['assets']: for asset in clip_data['assets']:
asset_url = asset.get('full_physical_path') asset_url = asset.get('full_physical_path')
if not asset_url: protocol = asset.get('protocol')
if not asset_url or protocol == 'primetime' or asset_url in urls:
continue continue
urls.append(asset_url)
container = asset.get('video_container') container = asset.get('video_container')
ext = determine_ext(asset_url) ext = determine_ext(asset_url)
if container == 'm3u8' or ext == 'm3u8': if container == 'm3u8' or ext == 'm3u8':
if protocol == 'usp':
asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native', asset_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)) m3u8_id='hls', fatal=False))
formats.extend(self._extract_f4m_formats( formats.extend(self._extract_f4m_formats(
asset_url.replace('.m3u8', '.f4m'), asset_url.replace('.m3u8', '.f4m'),
video_id, f4m_id='hds', fatal=False)) video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
asset_url.replace('.m3u8', '.mpd'),
video_id, mpd_id='dash', fatal=False))
formats.extend(self._extract_ism_formats(
re.sub('/[^/]+\.m3u8', '/Manifest', asset_url),
video_id, ism_id='mss', fatal=False))
else:
formats.extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif container == 'mp4' or ext == 'mp4': elif container == 'mp4' or ext == 'mp4':
quality = asset.get('video_quality') quality = asset.get('video_quality')
formats.append({ formats.append({