mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 10:52:34 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master'

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-11-09 08:30:12 +01:00
commit 8bb9b97c97
7 changed files with 67 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
youtube_dl/extractor/__init__.py
View File

@ -421,6 +421,7 @@
from .vevo import VevoIE
from .vgtv import VGTVIE
from .vh1 import VH1IE
from .vice import ViceIE
from .viddler import ViddlerIE
from .videobam import VideoBamIE
from .videodetective import VideoDetectiveIE

1
youtube_dl/extractor/generic.py
View File

@ -576,6 +576,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': os.path.splitext(url_basename(url))[0],
'direct': True,
'formats': [{
'format_id': m.group('format_id'),
'url': url,

43
youtube_dl/extractor/goshgay.py
View File

@ -1,15 +1,11 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
str_to_int,
ExtractorError,
)
import json
class GoshgayIE(InfoExtractor):
@ -27,36 +23,27 @@ class GoshgayIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title')
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
family_friendly = self._html_search_meta(
'isFamilyFriendly', webpage, default='false')
config_url = self._search_regex(
r"'config'\s*:\s*'([^']+)'", webpage, 'config URL')
player_config = self._search_regex(
r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings')
player_vars = json.loads(player_config.replace("'", '"'))
width = str_to_int(player_vars.get('width'))
height = str_to_int(player_vars.get('height'))
config_uri = player_vars.get('config')
config = self._download_xml(
config_url, video_id, 'Downloading player config XML')
if config_uri is None:
raise ExtractorError('Missing config URI')
node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
errnote='Unable to download XML')
if node is None:
if config is None:
raise ExtractorError('Missing config XML')
if node.tag != 'config':
if config.tag != 'config':
raise ExtractorError('Missing config attribute')
fns = node.findall('file')
imgs = node.findall('image')
if len(fns) != 1:
fns = config.findall('file')
if len(fns) < 1:
raise ExtractorError('Missing media URI')
video_url = fns[0].text
if len(imgs) < 1:
thumbnail = None
else:
thumbnail = imgs[0].text
url_comp = compat_urlparse.urlparse(url)
ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
@ -65,9 +52,7 @@ def _real_extract(self, url):
'id': video_id,
'url': video_url,
'title': title,
'width': width,
'height': height,
'thumbnail': thumbnail,
'http_referer': ref,
'age_limit': 18,
'age_limit': 0 if family_friendly == 'true' else 18,
}

3
youtube_dl/extractor/niconico.py
View File

@ -175,7 +175,8 @@ def _real_extract(self, url):
entries = [{
'_type': 'url',
'ie_key': NiconicoIE.ie_key(),
'url': 'http://www.nicovideo.jp/watch/%s' % entry['item_id'],
'url': ('http://www.nicovideo.jp/watch/%s' %
entry['item_data']['video_id']),
} for entry in entries]
return {

38
youtube_dl/extractor/vice.py Normal file
View File

@ -0,0 +1,38 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import ExtractorError
class ViceIE(InfoExtractor):
_VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
_TEST = {
'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
'info_dict': {
'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
'ext': 'mp4',
'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
},
'params': {
# Requires ffmpeg (m3u8 manifest)
'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
try:
embed_code = self._search_regex(
r'embedCode=([^&\'"]+)', webpage,
'ooyala embed code')
ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
print(ooyala_url)
except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True)
return self.url_result(ooyala_url, ie='Ooyala')

2
youtube_dl/extractor/wrzuta.py
View File

@ -49,7 +49,7 @@ def _real_extract(self, url):
quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
audio_table = {'flv': 'mp3', 'webm': 'ogg'}
audio_table = {'flv': 'mp3', 'webm': 'ogg', 'mp3': 'mp3'}
embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id)

11
youtube_dl/options.py
View File

@ -261,7 +261,16 @@ def _hide_login_info(opts):
video_format.add_option(
'-f', '--format',
action='store', dest='format', metavar='FORMAT', default=None,
help='video format code, specify the order of preference using slashes: -f 22/17/18 . -f mp4 , -f m4a and -f flv are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality. Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio')
help='video format code, specify the order of preference using'
' slashes: -f 22/17/18 . -f mp4 , -f m4a and -f flv are also'
' supported. You can also use the special names "best",'
' "bestvideo", "bestaudio", "worst", "worstvideo" and'
' "worstaudio". By default, youtube-dl will pick the best quality.'
' Use commas to download multiple audio formats, such as'
' -f 136/137/mp4/bestvideo,140/m4a/bestaudio.'
' You can merge the video and audio of two formats into a single'
' file using -f <video-format>+<audio-format> (requires ffmpeg or'
' avconv), for example -f bestvideo+bestaudio.')
video_format.add_option(
'--all-formats',
action='store_const', dest='format', const='all',