-import json
-import re
+from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import (
- compat_str,
+from ..compat import (
compat_urllib_parse,
-
+)
+from ..utils import (
ExtractorError,
+ js_to_json,
)
class EscapistIE(InfoExtractor):
- _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+ _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
_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'c6793dbda81388f4264c1ba18684a74d',
- 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_id': 'the-escapist-presents',
+ 'uploader': 'The Escapist Presents',
+ 'title': "Breaking Down Baldur's Gate",
+ 'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- showName = mobj.group('showname')
- videoId = mobj.group('episode')
-
- self.report_extraction(videoId)
- webpage = self._download_webpage(url, videoId)
-
- videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
- webpage, u'description', fatal=False)
-
- playerUrl = self._og_search_video_url(webpage, name='player url')
-
- title = self._html_search_regex('<meta name="title" content="([^"]*)"',
- webpage, u'player url').split(' : ')[-1]
-
- configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
- configUrl = compat_urllib_parse.unquote(configUrl)
-
- configJSON = self._download_webpage(configUrl, videoId,
- u'Downloading configuration',
- u'unable to download configuration')
-
- # Technically, it's JavaScript, not JSON
- configJSON = configJSON.replace("'", '"')
-
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ uploader_id = self._html_search_regex(
+ r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
+ webpage, 'uploader ID', fatal=False)
+ uploader = self._html_search_regex(
+ r"<h1\s+class='headline'>(.*?)</a>",
+ webpage, 'uploader', fatal=False)
+ description = self._html_search_meta('description', webpage)
+
+ raw_title = self._html_search_meta('title', webpage, fatal=True)
+ title = raw_title.partition(' : ')[2]
+
+ config_url = compat_urllib_parse.unquote(self._html_search_regex(
+ r'''(?x)
+ (?:
+ <param\s+name="flashvars".*?\s+value="config=|
+ flashvars="config=
+ )
+ (https?://[^"&]+)
+ ''',
+ webpage, 'config URL'))
+
+ formats = []
+ ad_formats = []
+
+ def _add_format(name, cfgurl, quality):
+ config = self._download_json(
+ cfgurl, video_id,
+ 'Downloading ' + name + ' configuration',
+ 'Unable to download ' + name + ' configuration',
+ transform_source=js_to_json)
+
+ playlist = config['playlist']
+ for p in playlist:
+ if p.get('eventCategory') == 'Video':
+ ar = formats
+ elif p.get('eventCategory') == 'Video Postroll':
+ ar = ad_formats
+ else:
+ continue
+
+ ar.append({
+ 'url': p['url'],
+ 'format_id': name,
+ 'quality': quality,
+ })
+
+ _add_format('normal', config_url, quality=0)
+ hq_url = (config_url +
+ ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
try:
- config = json.loads(configJSON)
- except (ValueError,) as err:
- raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
-
- playlist = config['playlist']
- videoUrl = playlist[1]['url']
-
- info = {
- 'id': videoId,
- 'url': videoUrl,
- 'uploader': showName,
- 'upload_date': None,
+ _add_format('hq', hq_url, quality=1)
+ except ExtractorError:
+ pass # That's fine, we'll just use normal quality
+ self._sort_formats(formats)
+
+ res = {
+ 'id': video_id,
+ 'formats': formats,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
'title': title,
- 'ext': 'mp4',
'thumbnail': self._og_search_thumbnail(webpage),
- 'description': videoDesc,
- 'player_url': playerUrl,
+ 'description': description,
}
- return [info]
+ if self._downloader.params.get('include_ads') and ad_formats:
+ self._sort_formats(ad_formats)
+ ad_res = {
+ 'id': '%s-ad' % video_id,
+ 'title': '%s (Postroll)' % title,
+ 'formats': ad_formats,
+ }
+ return {
+ '_type': 'playlist',
+ 'entries': [res, ad_res],
+ 'title': title,
+ 'id': video_id,
+ }
+
+ return res
projects / youtube-dl / blobdiff