github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[discovery] use API call for video data extraction(#21808)

Browse source
This commit is contained in:
Remita Amine 2019-08-01 22:44:38 +01:00
parent 826dcff99c
commit 535111657b
1 changed files with 26 additions and 33 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

55
youtube_dl/extractor/discovery.py
View file

@ -5,14 +5,8 @@ import re
import string import string
from .discoverygo import DiscoveryGoBaseIE from .discoverygo import DiscoveryGoBaseIE
from ..compat import ( from ..compat import compat_urllib_parse_unquote
compat_str, from ..utils import ExtractorError
compat_urllib_parse_unquote,
)
from ..utils import (
ExtractorError,
try_get,
)
from ..compat import compat_HTTPError from ..compat import compat_HTTPError
@ -40,15 +34,15 @@ class DiscoveryIE(DiscoveryGoBaseIE):
cookingchanneltv| cookingchanneltv|
motortrend motortrend
) )
)\.com(?P<path>/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+))''' )\.com/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+)'''
_TESTS = [{ _TESTS = [{
'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley', 'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry',
'info_dict': { 'info_dict': {
'id': '5a2d9b4d6b66d17a5026e1fd', 'id': '5a2f35ce6b66d17a5026e29e',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Dave Foley', 'title': 'Riding with Matthew Perry',
'description': 'md5:4b39bcafccf9167ca42810eb5f28b01f', 'description': 'md5:a34333153e79bc4526019a5129e7f878',
'duration': 608, 'duration': 84,
}, },
'params': { 'params': {
'skip_download': True, # requires ffmpeg 'skip_download': True, # requires ffmpeg
@ -62,17 +56,10 @@ class DiscoveryIE(DiscoveryGoBaseIE):
}] }]
_GEO_COUNTRIES = ['US'] _GEO_COUNTRIES = ['US']
_GEO_BYPASS = False _GEO_BYPASS = False
_API_BASE_URL = 'https://api.discovery.com/v1/'
def _real_extract(self, url): def _real_extract(self, url):
site, path, display_id = re.match(self._VALID_URL, url).groups() site, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
react_data = self._parse_json(self._search_regex(
r'window\.__reactTransmitPacket\s*=\s*({.+?});',
webpage, 'react data'), display_id)
content_blocks = react_data['layout'][path]['contentBlocks']
video = next(cb for cb in content_blocks if cb.get('type') == 'video')['content']['items'][0]
video_id = video['id']
access_token = None access_token = None
cookies = self._get_cookies(url) cookies = self._get_cookies(url)
@ -82,27 +69,33 @@ class DiscoveryIE(DiscoveryGoBaseIE):
if auth_storage_cookie and auth_storage_cookie.value: if auth_storage_cookie and auth_storage_cookie.value:
auth_storage = self._parse_json(compat_urllib_parse_unquote( auth_storage = self._parse_json(compat_urllib_parse_unquote(
compat_urllib_parse_unquote(auth_storage_cookie.value)), compat_urllib_parse_unquote(auth_storage_cookie.value)),
video_id, fatal=False) or {} display_id, fatal=False) or {}
access_token = auth_storage.get('a') or auth_storage.get('access_token') access_token = auth_storage.get('a') or auth_storage.get('access_token')
if not access_token: if not access_token:
access_token = self._download_json( access_token = self._download_json(
'https://%s.com/anonymous' % site, display_id, query={ 'https://%s.com/anonymous' % site, display_id,
'Downloading token JSON metadata', query={
'authRel': 'authorization', 'authRel': 'authorization',
'client_id': try_get( 'client_id': '3020a40c2356a645b4b4',
react_data, lambda x: x['application']['apiClientId'],
compat_str) or '3020a40c2356a645b4b4',
'nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), 'nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]),
'redirectUri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html?https://www.%s.com' % site, 'redirectUri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html?https://www.%s.com' % site,
})['access_token'] })['access_token']
try:
headers = self.geo_verification_headers() headers = self.geo_verification_headers()
headers['Authorization'] = 'Bearer ' + access_token headers['Authorization'] = 'Bearer ' + access_token
try:
video = self._download_json(
self._API_BASE_URL + 'content/videos',
display_id, 'Downloading content JSON metadata',
headers=headers, query={
'slug': display_id,
})[0]
video_id = video['id']
stream = self._download_json( stream = self._download_json(
'https://api.discovery.com/v1/streaming/video/' + video_id, self._API_BASE_URL + 'streaming/video/' + video_id,
display_id, headers=headers) display_id, 'Downloading streaming JSON metadata', headers=headers)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
e_description = self._parse_json( e_description = self._parse_json(