[extractor,cleanup] Use _search_nextjs_data

This commit is contained in:
pukkandan 2022-01-20 03:25:15 +05:30
parent e0585e6562
commit 135dfa2c7e
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
8 changed files with 12 additions and 26 deletions

View File

@ -1544,12 +1544,12 @@ class InfoExtractor(object):
return dict((k, v) for k, v in info.items() if v is not None)
def _search_nextjs_data(self, webpage, video_id, **kw):
def _search_nextjs_data(self, webpage, video_id, *, transform_source=None, fatal=True, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', **kw),
video_id, **kw)
webpage, 'next.js data', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__'):
''' Parses Nuxt.js metadata. This works as long as the function __NUXT__ invokes is a pure function. '''

View File

@ -243,8 +243,8 @@ class ITVBTCCIE(InfoExtractor):
webpage = self._download_webpage(url, playlist_id)
json_map = try_get(self._parse_json(self._html_search_regex(
'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[^>]*>([^<]+)</script>', webpage, 'json_map'), playlist_id),
json_map = try_get(
self._search_nextjs_data(webpage, playlist_id),
lambda x: x['props']['pageProps']['article']['body']['content']) or []
entries = []

View File

@ -408,9 +408,7 @@ class NBCNewsIE(ThePlatformIE):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._parse_json(self._search_regex(
r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>',
webpage, 'bootstrap json'), video_id)['props']['initialState']
data = self._search_nextjs_data(webpage, video_id)['props']['initialState']
video_data = try_get(data, lambda x: x['video']['current'], dict)
if not video_data:
video_data = data['article']['content'][0]['primaryMedia']['video']

View File

@ -41,9 +41,7 @@ class NovaPlayIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_props = self._parse_json(self._search_regex(
r'<script\s?id=\"__NEXT_DATA__\"\s?type=\"application/json\">({.+})</script>',
webpage, 'video_props'), video_id)['props']['pageProps']['video']
video_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['video']
m3u8_url = self._download_json(
f'https://nbg-api.fite.tv/api/v2/videos/{video_id}/streams',
video_id, headers={'x-flipps-user-agent': 'Flipps/75/9.7'})[0]['url']

View File

@ -3,7 +3,6 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_parse_qs,
compat_urllib_parse_urlparse,
)
@ -125,9 +124,7 @@ class SkyItVideoLiveIE(SkyItPlayerIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
asset_id = compat_str(self._parse_json(self._search_regex(
r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>',
webpage, 'next data'), display_id)['props']['initialState']['livePage']['content']['asset_id'])
asset_id = str(self._search_nextjs_data(webpage, display_id)['props']['initialState']['livePage']['content']['asset_id'])
livestream = self._download_json(
'https://apid.sky.it/vdp/v1/getLivestream',
asset_id, query={'id': asset_id})

View File

@ -45,10 +45,7 @@ class STVPlayerIE(InfoExtractor):
ptype, video_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, video_id, fatal=False) or ''
props = (self._parse_json(self._search_regex(
r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>',
webpage, 'next data', default='{}'), video_id,
fatal=False) or {}).get('props') or {}
props = self._search_nextjs_data(webpage, video_id, default='{}').get('props') or {}
player_api_cache = try_get(
props, lambda x: x['initialReduxState']['playerApiCache']) or {}

View File

@ -34,8 +34,7 @@ class TelemundoIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
metadata = self._parse_json(
self._search_regex(r'<[^>]+id="__NEXT_DATA__"[^>]+>([^<]+)', webpage, 'JSON metadata'), video_id)
metadata = self._search_nextjs_data(webpage, video_id)
redirect_url = try_get(
metadata,
lambda x: x['props']['initialState']['video']['associatedPlaylists'][0]['videos'][0]['videoAssets'][0]['publicUrl'])

View File

@ -451,12 +451,9 @@ class TikTokIE(TikTokBaseIE):
# If we only call once, we get a 403 when downlaoding the video.
self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id, note='Downloading video webpage')
next_json = self._search_regex(
r'id=\"__NEXT_DATA__\"\s+type=\"application\/json\"\s*[^>]+>\s*(?P<next_data>[^<]+)',
webpage, 'next data', group='next_data', default=None)
next_data = self._search_nextjs_data(webpage, video_id, default='{}')
if next_json:
next_data = self._parse_json(next_json, video_id)
if next_data:
status = traverse_obj(next_data, ('props', 'pageProps', 'statusCode'), expected_type=int) or 0
video_data = traverse_obj(next_data, ('props', 'pageProps', 'itemInfo', 'itemStruct'), expected_type=dict)
else: