dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[escapist] Modernize

This commit is contained in:
Philipp Hagemeister 2015-02-10 15:45:36 +01:00
parent 612ee37365
commit 596ac6e31f
1 changed files with 25 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
youtube_dl/extractor/escapist.py
View File

@ -1,18 +1,17 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse, compat_urllib_parse,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
js_to_json,
) )
class EscapistIE(InfoExtractor): class EscapistIE(InfoExtractor):
_VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-' _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
_TEST = { _TEST = {
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1', 'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
@ -20,31 +19,30 @@ class EscapistIE(InfoExtractor):
'id': '6618', 'id': '6618',
'ext': 'mp4', '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.", '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', 'uploader_id': 'the-escapist-presents',
'uploader': 'The Escapist Presents',
'title': "Breaking Down Baldur's Gate", 'title': "Breaking Down Baldur's Gate",
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
showName = mobj.group('showname')
video_id = mobj.group('id')
self.report_extraction(video_id)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
videoDesc = self._html_search_regex( uploader_id = self._html_search_regex(
r'<meta name="description" content="([^"]*)"', r"<h1 class='headline'><a href='/videos/view/(.*?)'",
webpage, 'description', fatal=False) webpage, 'uploader ID', fatal=False)
uploader = self._html_search_regex(
r"<h1 class='headline'>(.*?)</a>",
webpage, 'uploader', fatal=False)
description = self._html_search_meta('description', webpage)
playerUrl = self._og_search_video_url(webpage, name='player URL') raw_title = self._html_search_meta('title', webpage, fatal=True)
title = raw_title.partition(' : ')[2]
title = self._html_search_regex( player_url = self._og_search_video_url(webpage, name='player URL')
r'<meta name="title" content="([^"]*)"', config_url = compat_urllib_parse.unquote(self._search_regex(
webpage, 'title').split(' : ')[-1] r'config=(.*)$', player_url, 'config URL'))
configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
configUrl = compat_urllib_parse.unquote(configUrl)
formats = [] formats = []
@ -53,7 +51,7 @@ class EscapistIE(InfoExtractor):
cfgurl, video_id, cfgurl, video_id,
'Downloading ' + name + ' configuration', 'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration', 'Unable to download ' + name + ' configuration',
transform_source=lambda s: s.replace("'", '"')) transform_source=js_to_json)
playlist = config['playlist'] playlist = config['playlist']
formats.append({ formats.append({
@ -62,9 +60,9 @@ class EscapistIE(InfoExtractor):
'quality': quality, 'quality': quality,
}) })
_add_format('normal', configUrl, quality=0) _add_format('normal', config_url, quality=0)
hq_url = (configUrl + hq_url = (config_url +
('&hq=1' if '?' in configUrl else configUrl + '?hq=1')) ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
try: try:
_add_format('hq', hq_url, quality=1) _add_format('hq', hq_url, quality=1)
except ExtractorError: except ExtractorError:
@ -75,9 +73,10 @@ class EscapistIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'uploader': showName, 'uploader': uploader,
'uploader_id': uploader_id,
'title': title, 'title': title,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'description': videoDesc, 'description': description,
'player_url': playerUrl, 'player_url': player_url,
} }