[aenetworks] improve format extraction

This commit is contained in:
remitamine 2016-04-01 09:56:18 +01:00
parent db1c969da5
commit d8873d4def

View File

@ -1,13 +1,19 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import smuggle_url from ..utils import (
smuggle_url,
update_url_query,
unescapeHTML,
)
class AENetworksIE(InfoExtractor): class AENetworksIE(InfoExtractor):
IE_NAME = 'aenetworks' IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
_VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])' _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?P<type>[^/]+)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
_TESTS = [{ _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', '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',
@ -25,16 +31,13 @@ class AENetworksIE(InfoExtractor):
'expected_warnings': ['JSON-LD'], 'expected_warnings': ['JSON-LD'],
}, { }, {
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
'info_dict': { 'info_dict': {
'id': 'eg47EERs_JsZ', 'id': 'eg47EERs_JsZ',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Winter Is Coming', 'title': 'Winter Is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
}, },
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'], 'add_ie': ['ThePlatform'],
}, { }, {
'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry', 'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
@ -48,7 +51,7 @@ class AENetworksIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) page_type, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
@ -56,11 +59,22 @@ def _real_extract(self, url):
r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id, r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
r"media_url\s*=\s*'([^']+)'" r"media_url\s*=\s*'([^']+)'"
] ]
video_url = self._search_regex(video_url_re, webpage, 'video url') video_url = unescapeHTML(self._search_regex(video_url_re, webpage, 'video url'))
query = {'mbr': 'true'}
if page_type == 'shows':
query['assetTypes'] = 'medium_video_s3'
if 'switch=hds' in video_url:
query['switch'] = 'hls'
info = self._search_json_ld(webpage, video_id, fatal=False) info = self._search_json_ld(webpage, video_id, fatal=False)
info.update({ info.update({
'_type': 'url_transparent', '_type': 'url_transparent',
'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}), 'url': smuggle_url(update_url_query(
video_url, query), {
'sig': {
'key': 'crazyjava',
'secret': 's3cr3t'},
'force_smil_url': True
}),
}) })
return info return info