archive
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[ie/litv] Fix extractor (#11071)

Browse Source 
Authored by: jiru
pull/11572/head
gillux 1 week ago committed by GitHub
parent 2009cb27e1
commit e079ffbda6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 50 additions and 81 deletions
Show Stats Download Patch File Download Diff File

119
yt_dlp/extractor/litv.py
Unescape Escape View File

@ -1,30 +1,32 @@
import json import json
import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
join_nonempty,
smuggle_url, smuggle_url,
traverse_obj, traverse_obj,
try_call, try_call,
unsmuggle_url, unsmuggle_url,
urljoin,
) )
class LiTVIE(InfoExtractor): class LiTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)' _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:[^/?#]+/watch/|vod/[^/?#]+/content\.do\?content_id=)(?P<id>[\w-]+)'
_URL_TEMPLATE = 'https://www.litv.tv/%s/watch/%s'
_URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?content_id=%s' _GEO_COUNTRIES = ['TW']
_TESTS = [{ _TESTS = [{
'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1', 'url': 'https://www.litv.tv/drama/watch/VOD00041610',
'info_dict': { 'info_dict': {
'id': 'VOD00041606', 'id': 'VOD00041606',
'title': '花千骨', 'title': '花千骨',
}, },
'playlist_count': 51, # 50 episodes + 1 trailer 'playlist_count': 51, # 50 episodes + 1 trailer
}, { }, {
'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1', 'url': 'https://www.litv.tv/drama/watch/VOD00041610',
'md5': 'b90ff1e9f1d8f5cfcd0a44c3e2b34c7a', 'md5': 'b90ff1e9f1d8f5cfcd0a44c3e2b34c7a',
'info_dict': { 'info_dict': {
'id': 'VOD00041610', 'id': 'VOD00041610',
@ -32,16 +34,15 @@ class LiTVIE(InfoExtractor):
'title': '花千骨第1集', 'title': '花千骨第1集',
'thumbnail': r're:https?://.*\.jpg$', 'thumbnail': r're:https?://.*\.jpg$',
'description': '《花千骨》陸劇線上看。十六年前，平靜的村莊內，一名女嬰隨異相出生，途徑此地的蜀山掌門清虛道長算出此女命運非同一般，她體內散發的異香易招惹妖魔。一念慈悲下，他在村莊周邊設下結界阻擋妖魔入侵，讓其年滿十六後去蜀山，並賜名花千骨。', 'description': '《花千骨》陸劇線上看。十六年前，平靜的村莊內，一名女嬰隨異相出生，途徑此地的蜀山掌門清虛道長算出此女命運非同一般，她體內散發的異香易招惹妖魔。一念慈悲下，他在村莊周邊設下結界阻擋妖魔入侵，讓其年滿十六後去蜀山，並賜名花千骨。',
'categories': ['奇幻', '愛情', '中國', '仙俠'], 'categories': ['奇幻', '愛情', '仙俠', '古裝'],
'episode': 'Episode 1', 'episode': 'Episode 1',
'episode_number': 1, 'episode_number': 1,
}, },
'params': { 'params': {
'noplaylist': True, 'noplaylist': True,
}, },
'skip': 'Georestricted to Taiwan',
}, { }, {
'url': 'https://www.litv.tv/promo/miyuezhuan/?content_id=VOD00044841&', 'url': 'https://www.litv.tv/drama/watch/VOD00044841',
'md5': '88322ea132f848d6e3e18b32a832b918', 'md5': '88322ea132f848d6e3e18b32a832b918',
'info_dict': { 'info_dict': {
'id': 'VOD00044841', 'id': 'VOD00044841',
@ -55,94 +56,62 @@ class LiTVIE(InfoExtractor):
def _extract_playlist(self, playlist_data, content_type): def _extract_playlist(self, playlist_data, content_type):
all_episodes = [ all_episodes = [
self.url_result(smuggle_url( self.url_result(smuggle_url(
self._URL_TEMPLATE % (content_type, episode['contentId']), self._URL_TEMPLATE % (content_type, episode['content_id']),
{'force_noplaylist': True})) # To prevent infinite recursion {'force_noplaylist': True})) # To prevent infinite recursion
for episode in traverse_obj(playlist_data, ('seasons', ..., 'episode', lambda _, v: v['contentId']))] for episode in traverse_obj(playlist_data, ('seasons', ..., 'episodes', lambda _, v: v['content_id']))]
return self.playlist_result(all_episodes, playlist_data['contentId'], playlist_data.get('title')) return self.playlist_result(all_episodes, playlist_data['content_id'], playlist_data.get('title'))
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
vod_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
if self._search_regex(
r'(?i)<meta\s[^>]*http-equiv="refresh"\s[^>]*content="[0-9]+;\s*url=https://www\.litv\.tv/"', program_info = traverse_obj(vod_data, ('programInformation', {dict})) or {}
webpage, 'meta refresh redirect', default=False, group=0): playlist_data = traverse_obj(vod_data, ('seriesTree'))
raise ExtractorError('No such content found', expected=True) if playlist_data and self._yes_playlist(program_info.get('series_id'), video_id, smuggled_data):
return self._extract_playlist(playlist_data, program_info.get('content_type'))
program_info = self._parse_json(self._search_regex(
r'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'), asset_id = traverse_obj(program_info, ('assets', 0, 'asset_id', {str}))
video_id) if asset_id: # This is a VOD
media_type = 'vod'
# In browsers `getProgramInfo` request is always issued. Usually this else: # This is a live stream
# endpoint gives the same result as the data embedded in the webpage. asset_id = program_info['content_id']
# If, for some reason, there are no embedded data, we do an extra request. media_type = program_info['content_type']
if 'assetId' not in program_info:
program_info = self._download_json(
'https://www.litv.tv/vod/ajax/getProgramInfo', video_id,
query={'contentId': video_id},
headers={'Accept': 'application/json'})
series_id = program_info['seriesId']
if self._yes_playlist(series_id, video_id, smuggled_data):
playlist_data = self._download_json(
'https://www.litv.tv/vod/ajax/getSeriesTree', video_id,
query={'seriesId': series_id}, headers={'Accept': 'application/json'})
return self._extract_playlist(playlist_data, program_info['contentType'])
video_data = self._parse_json(self._search_regex(
r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
webpage, 'video data', default='{}'), video_id)
if not video_data:
payload = {'assetId': program_info['assetId']}
puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value) puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value)
if puid: if puid:
payload.update({ endpoint = 'get-urls'
'type': 'auth',
'puid': puid,
})
endpoint = 'getUrl'
else: else:
payload.update({ puid = str(uuid.uuid4())
'watchDevices': program_info['watchDevices'], endpoint = 'get-urls-no-auth'
'contentType': program_info['contentType'],
})
endpoint = 'getMainUrlNoAuth'
video_data = self._download_json( video_data = self._download_json(
f'https://www.litv.tv/vod/ajax/{endpoint}', video_id, f'https://www.litv.tv/api/{endpoint}', video_id,
data=json.dumps(payload).encode(), data=json.dumps({'AssetId': asset_id, 'MediaType': media_type, 'puid': puid}).encode(),
headers={'Content-Type': 'application/json'}) headers={'Content-Type': 'application/json'})
if not video_data.get('fullpath'): if error := traverse_obj(video_data, ('error', {dict})):
error_msg = video_data.get('errorMessage') error_msg = traverse_obj(error, ('message', {str}))
if error_msg == 'vod.error.outsideregionerror': if error_msg and 'OutsideRegionError' in error_msg:
self.raise_geo_restricted('This video is available in Taiwan only') self.raise_geo_restricted('This video is available in Taiwan only')
if error_msg: elif error_msg:
raise ExtractorError(f'{self.IE_NAME} said: {error_msg}', expected=True) raise ExtractorError(f'{self.IE_NAME} said: {error_msg}', expected=True)
raise ExtractorError(f'Unexpected result from {self.IE_NAME}') raise ExtractorError(f'Unexpected error from {self.IE_NAME}')
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
video_data['fullpath'], video_id, ext='mp4', video_data['result']['AssetURLs'][0], video_id, ext='mp4', m3u8_id='hls')
entry_protocol='m3u8_native', m3u8_id='hls')
for a_format in formats: for a_format in formats:
# LiTV HLS segments doesn't like compressions # LiTV HLS segments doesn't like compressions
a_format.setdefault('http_headers', {})['Accept-Encoding'] = 'identity' a_format.setdefault('http_headers', {})['Accept-Encoding'] = 'identity'
title = program_info['title'] + program_info.get('secondaryMark', '')
description = program_info.get('description')
thumbnail = program_info.get('imageFile')
categories = [item['name'] for item in program_info.get('category', [])]
episode = int_or_none(program_info.get('episode'))
return { return {
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'title': title, 'title': join_nonempty('title', 'secondary_mark', delim='', from_dict=program_info),
'description': description, **traverse_obj(program_info, {
'thumbnail': thumbnail, 'description': ('description', {str}),
'categories': categories, 'thumbnail': ('picture', {urljoin('https://p-cdnstatic.svc.litv.tv/')}),
'episode_number': episode, 'categories': ('genres', ..., 'name', {str}),
'episode_number': ('episode', {int_or_none}),
}),
} }

Write Preview
Loading…
Cancel
Save