2015-02-14 14:57:52 -08:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2016-04-01 01:56:18 -07:00
|
|
|
import re
|
|
|
|
|
2015-02-14 14:57:52 -08:00
|
|
|
from .common import InfoExtractor
|
2016-04-01 01:56:18 -07:00
|
|
|
from ..utils import (
|
|
|
|
smuggle_url,
|
|
|
|
update_url_query,
|
|
|
|
unescapeHTML,
|
2016-06-29 07:49:17 -07:00
|
|
|
extract_attributes,
|
2016-06-29 08:18:16 -07:00
|
|
|
get_element_by_attribute,
|
2016-04-01 01:56:18 -07:00
|
|
|
)
|
2016-06-29 07:49:17 -07:00
|
|
|
from ..compat import (
|
|
|
|
compat_urlparse,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
class AENetworksBaseIE(InfoExtractor):
|
|
|
|
def theplatform_url_result(self, theplatform_url, video_id, query):
|
|
|
|
return {
|
|
|
|
'_type': 'url_transparent',
|
|
|
|
'id': video_id,
|
|
|
|
'url': smuggle_url(
|
|
|
|
update_url_query(theplatform_url, query),
|
|
|
|
{
|
|
|
|
'sig': {
|
|
|
|
'key': 'crazyjava',
|
|
|
|
'secret': 's3cr3t'
|
|
|
|
},
|
|
|
|
'force_smil_url': True
|
|
|
|
}),
|
|
|
|
'ie_key': 'ThePlatform',
|
|
|
|
}
|
2015-02-14 14:57:52 -08:00
|
|
|
|
|
|
|
|
2016-06-29 07:49:17 -07:00
|
|
|
class AENetworksIE(AENetworksBaseIE):
|
2016-01-16 13:02:45 -08:00
|
|
|
IE_NAME = 'aenetworks'
|
|
|
|
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
|
2016-06-29 07:49:17 -07:00
|
|
|
_VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/shows/(?P<id>[^/]+(?:/[^/]+){0,2})'
|
2015-02-14 14:57:52 -08:00
|
|
|
_TESTS = [{
|
2016-01-15 06:16:57 -08:00
|
|
|
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
|
2016-04-01 01:56:18 -07:00
|
|
|
'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
|
2016-01-15 06:16:57 -08:00
|
|
|
'info_dict': {
|
2016-06-29 07:49:17 -07:00
|
|
|
'id': '22253814',
|
2016-01-15 06:16:57 -08:00
|
|
|
'ext': 'mp4',
|
2016-02-14 01:37:17 -08:00
|
|
|
'title': 'Winter Is Coming',
|
2016-01-16 04:56:53 -08:00
|
|
|
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
|
2016-04-01 10:06:11 -07:00
|
|
|
'timestamp': 1338306241,
|
|
|
|
'upload_date': '20120529',
|
|
|
|
'uploader': 'AENE-NEW',
|
2016-01-15 06:16:57 -08:00
|
|
|
},
|
2015-02-14 14:57:52 -08:00
|
|
|
'add_ie': ['ThePlatform'],
|
2016-01-15 07:18:07 -08:00
|
|
|
}, {
|
2016-06-29 07:49:17 -07:00
|
|
|
'url': 'http://www.history.com/shows/ancient-aliens/season-1',
|
|
|
|
'info_dict': {
|
|
|
|
'id': '71889446852',
|
|
|
|
},
|
|
|
|
'playlist_mincount': 5,
|
|
|
|
}, {
|
|
|
|
'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'SERIES4317',
|
|
|
|
'title': 'Atlanta Plastic',
|
|
|
|
},
|
|
|
|
'playlist_mincount': 2,
|
|
|
|
}, {
|
|
|
|
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
|
2016-01-15 07:18:07 -08:00
|
|
|
'only_matching': True
|
|
|
|
}, {
|
2016-06-29 07:49:17 -07:00
|
|
|
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
|
2016-01-15 07:18:07 -08:00
|
|
|
'only_matching': True
|
|
|
|
}, {
|
2016-06-29 07:49:17 -07:00
|
|
|
'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
|
2016-01-15 07:18:07 -08:00
|
|
|
'only_matching': True
|
2015-02-14 14:57:52 -08:00
|
|
|
}]
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2016-06-29 07:49:17 -07:00
|
|
|
display_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(url, display_id)
|
|
|
|
url_parts = display_id.split('/')
|
|
|
|
url_parts_len = len(url_parts)
|
|
|
|
if url_parts_len == 1:
|
|
|
|
entries = []
|
|
|
|
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
|
|
|
|
entries.append(self.url_result(
|
|
|
|
compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
|
|
|
|
return self.playlist_result(
|
|
|
|
entries, self._html_search_meta('aetn:SeriesId', webpage),
|
|
|
|
self._html_search_meta('aetn:SeriesTitle', webpage))
|
|
|
|
elif url_parts_len == 2:
|
|
|
|
entries = []
|
|
|
|
for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
|
|
|
|
episode_attributes = extract_attributes(episode_item)
|
|
|
|
episode_url = compat_urlparse.urljoin(
|
|
|
|
url, episode_attributes['data-canonical'])
|
|
|
|
entries.append(self.url_result(
|
|
|
|
episode_url, 'AENetworks',
|
|
|
|
episode_attributes['data-videoid']))
|
|
|
|
return self.playlist_result(
|
|
|
|
entries, self._html_search_meta('aetn:SeasonId', webpage))
|
|
|
|
else:
|
|
|
|
video_id = self._html_search_meta('aetn:VideoID', webpage)
|
|
|
|
media_url = self._search_regex(
|
|
|
|
r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
|
2015-02-14 14:57:52 -08:00
|
|
|
|
2016-06-29 07:49:17 -07:00
|
|
|
info = self._search_json_ld(webpage, video_id, fatal=False)
|
|
|
|
info.update(self.theplatform_url_result(
|
|
|
|
media_url, video_id, {
|
|
|
|
'mbr': 'true',
|
|
|
|
'assetTypes': 'medium_video_s3'
|
|
|
|
}))
|
|
|
|
return info
|
2015-02-14 14:57:52 -08:00
|
|
|
|
|
|
|
|
2016-06-29 07:49:17 -07:00
|
|
|
class HistoryTopicIE(AENetworksBaseIE):
|
|
|
|
IE_NAME = 'history:topic'
|
|
|
|
IE_DESC = 'History.com Topic'
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)/videos(?:/(?P<display_id>[^/?#]+))?'
|
|
|
|
_TESTS = [{
|
|
|
|
'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
|
|
|
|
'info_dict': {
|
|
|
|
'id': '40700995724',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': "Bet You Didn't Know: Valentine's Day",
|
|
|
|
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
|
|
|
|
'timestamp': 1375819729,
|
|
|
|
'upload_date': '20130806',
|
|
|
|
'uploader': 'AENE-NEW',
|
|
|
|
},
|
|
|
|
'params': {
|
|
|
|
# m3u8 download
|
|
|
|
'skip_download': True,
|
|
|
|
},
|
|
|
|
'add_ie': ['ThePlatform'],
|
|
|
|
}, {
|
|
|
|
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
|
|
|
|
'info_dict':
|
|
|
|
{
|
|
|
|
'id': 'world-war-i-history',
|
2016-06-29 08:18:16 -07:00
|
|
|
'title': 'World War I History',
|
2016-06-29 07:49:17 -07:00
|
|
|
},
|
|
|
|
'playlist_mincount': 24,
|
|
|
|
}, {
|
|
|
|
'url': 'http://www.history.com/topics/world-war-i-history/videos',
|
|
|
|
'only_matching': True,
|
|
|
|
}]
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
topic_id, display_id = re.match(self._VALID_URL, url).groups()
|
|
|
|
if display_id:
|
|
|
|
webpage = self._download_webpage(url, display_id)
|
|
|
|
release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
|
|
|
|
release_url = unescapeHTML(release_url)
|
|
|
|
|
|
|
|
return self.theplatform_url_result(
|
|
|
|
release_url, video_id, {
|
|
|
|
'mbr': 'true',
|
|
|
|
'switch': 'hls'
|
|
|
|
})
|
|
|
|
else:
|
|
|
|
webpage = self._download_webpage(url, topic_id)
|
|
|
|
entries = []
|
|
|
|
for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
|
|
|
|
video_attributes = extract_attributes(episode_item)
|
|
|
|
entries.append(self.theplatform_url_result(
|
2016-06-29 08:03:32 -07:00
|
|
|
video_attributes['data-release-url'], video_attributes['data-id'], {
|
2016-06-29 07:49:17 -07:00
|
|
|
'mbr': 'true',
|
|
|
|
'switch': 'hls'
|
|
|
|
}))
|
2016-06-29 08:18:16 -07:00
|
|
|
return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))
|