Mirror
/
youtube-dl
mirror of https://github.com/ytdl-org/youtube-dl.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[ecapist] modernize and fix id property

pull/2394/head
Philipp Hagemeister 2014-02-13 16:32:42 +01:00
parent 0715161450
commit 6f90d098c5
1 changed files with 29 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
youtube_dl/extractor/escapist.py
View File

@ -1,9 +1,9 @@
import json
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
ExtractorError,
@ -11,70 +11,68 @@ from ..utils import (
class EscapistIE(InfoExtractor):
_VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
_VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
_TEST = {
u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
u'info_dict': {
u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
u"uploader": u"the-escapist-presents",
u"title": u"Breaking Down Baldur's Gate"
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
'info_dict': {
'id': '6618',
'ext': 'mp4',
'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
'uploader': 'the-escapist-presents',
'title': "Breaking Down Baldur's Gate",
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
video_id = mobj.group('id')
self.report_extraction(videoId)
webpage = self._download_webpage(url, videoId)
self.report_extraction(video_id)
webpage = self._download_webpage(url, video_id)
videoDesc = self._html_search_regex(
r'<meta name="description" content="([^"]*)"',
webpage, u'description', fatal=False)
webpage, 'description', fatal=False)
playerUrl = self._og_search_video_url(webpage, name=u'player URL')
title = self._html_search_regex(
r'<meta name="title" content="([^"]*)"',
webpage, u'title').split(' : ')[-1]
webpage, 'title').split(' : ')[-1]
configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
configUrl = compat_urllib_parse.unquote(configUrl)
formats = []
def _add_format(name, cfgurl):
configJSON = self._download_webpage(
cfgurl, videoId,
u'Downloading ' + name + ' configuration',
u'Unable to download ' + name + ' configuration')
def _add_format(name, cfgurl, quality):
config = self._download_json(
cfgurl, video_id,
'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration',
transform_source=lambda s: s.replace("'", '"'))
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
try:
config = json.loads(configJSON)
except (ValueError,) as err:
raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
formats.append({
'url': playlist[1]['url'],
'format_id': name,
'quality': quality,
})
_add_format(u'normal', configUrl)
_add_format('normal', configUrl, quality=0)
hq_url = (configUrl +
('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
try:
_add_format(u'hq', hq_url)
_add_format('hq', hq_url, quality=1)
except ExtractorError:
pass # That's fine, we'll just use normal quality
self._sort_formats(formats)
return {
'id': videoId,
'id': video_id,
'formats': formats,
'uploader': showName,
'title': title,