yt-dlp/youtube_dl/extractor/escapist.py

113 lines
3.8 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 21:08:17 +02:00
from .common import InfoExtractor
from ..compat import (
2013-06-23 21:08:17 +02:00
compat_urllib_parse,
)
from ..utils import (
2013-06-23 21:08:17 +02:00
ExtractorError,
2015-02-10 15:45:36 +01:00
js_to_json,
2013-06-23 21:08:17 +02:00
)
class EscapistIE(InfoExtractor):
2015-02-10 15:45:36 +01:00
_VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
2013-06-27 20:46:46 +02:00
_TEST = {
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
'info_dict': {
'id': '6618',
'ext': 'mp4',
'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
2015-02-10 15:45:36 +01:00
'uploader_id': 'the-escapist-presents',
'uploader': 'The Escapist Presents',
'title': "Breaking Down Baldur's Gate",
'thumbnail': 're:^https?://.*\.jpg$',
2013-06-27 20:46:46 +02:00
}
}
2013-06-23 21:08:17 +02:00
def _real_extract(self, url):
2015-02-10 15:45:36 +01:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2013-06-23 21:08:17 +02:00
2015-02-10 15:45:36 +01:00
uploader_id = self._html_search_regex(
r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
2015-02-10 15:45:36 +01:00
webpage, 'uploader ID', fatal=False)
uploader = self._html_search_regex(
r"<h1\s+class='headline'>(.*?)</a>",
2015-02-10 15:45:36 +01:00
webpage, 'uploader', fatal=False)
description = self._html_search_meta('description', webpage)
2013-06-23 21:08:17 +02:00
2015-02-10 15:45:36 +01:00
raw_title = self._html_search_meta('title', webpage, fatal=True)
title = raw_title.partition(' : ')[2]
2013-06-23 21:08:17 +02:00
config_url = compat_urllib_parse.unquote(self._html_search_regex(
r'''(?x)
(?:
2015-02-26 00:24:54 +01:00
<param\s+name="flashvars".*?\s+value="config=|
flashvars=&quot;config=
)
2015-02-26 00:24:54 +01:00
(https?://[^"&]+)
''',
webpage, 'config URL'))
2013-06-23 21:08:17 +02:00
formats = []
ad_formats = []
2013-06-23 21:08:17 +02:00
def _add_format(name, cfgurl, quality):
config = self._download_json(
cfgurl, video_id,
'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration',
2015-02-10 15:45:36 +01:00
transform_source=js_to_json)
2013-06-23 21:08:17 +02:00
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,
})
2013-06-23 21:08:17 +02:00
2015-02-10 15:45:36 +01:00
_add_format('normal', config_url, quality=0)
hq_url = (config_url +
('&hq=1' if '?' in config_url else config_url + '?hq=1'))
try:
_add_format('hq', hq_url, quality=1)
2013-11-20 06:55:07 +01:00
except ExtractorError:
pass # That's fine, we'll just use normal quality
self._sort_formats(formats)
res = {
'id': video_id,
'formats': formats,
2015-02-10 15:45:36 +01:00
'uploader': uploader,
'uploader_id': uploader_id,
2013-06-23 21:08:17 +02:00
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
2015-02-10 15:45:36 +01:00
'description': description,
2013-06-23 21:08:17 +02:00
}
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