Compare commits

...

5 Commits

Author SHA1 Message Date
Ali Madihi
615e5e7b09
Merge 49a68705dc7c506b35b4c4e7f83a132acad43c91 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 10:33:45 +02:00
dirkf
3eb8d22ddb
[JSInterp] Temporary fix for #33102 2025-03-31 04:21:09 +01:00
dirkf
4e714f9df1 [Misc] Correct [_]IE_DESC/NAME in a few IEs
* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`
2025-03-26 12:47:19 +00:00
dirkf
c1ea7f5a24 [ITV] Mark ITVX not working
* update old shim
* correct [_]IE_DESC
2025-03-26 12:17:49 +00:00
ali madihi
49a68705dc [namava] Add new extractor 2021-04-01 21:46:01 +04:30
8 changed files with 110 additions and 15 deletions

View File

@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
IE_DESC = 'CC视频'
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{

View File

@ -9,7 +9,7 @@ from ..utils import (
class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec'
IE_DESC = 'cloudy.ec'
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac',

View File

@ -422,6 +422,8 @@ class InfoExtractor(object):
_GEO_COUNTRIES = None
_GEO_IP_BLOCKS = None
_WORKING = True
# supply this in public subclasses: used in supported sites list, etc
# IE_DESC = 'short description of IE'
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""

View File

@ -746,6 +746,7 @@ from .myvi import (
)
from .myvideoge import MyVideoGeIE
from .myvidster import MyVidsterIE
from .namava import NamavaIE
from .nationalgeographic import (
NationalGeographicVideoIE,
NationalGeographicTVIE,

View File

@ -35,15 +35,6 @@ from ..utils import (
class ITVBaseIE(InfoExtractor):
def _search_nextjs_data(self, webpage, video_id, **kw):
transform_source = kw.pop('transform_source', None)
fatal = kw.pop('fatal', True)
return self._parse_json(
self._search_regex(
r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
webpage, 'next.js data', group='js', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False:
return False
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
_IE_DESC = 'ITVX'
IE_DESC = 'ITVX'
_WORKING = False
_TESTS = [{
'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'ext': determine_ext(href, 'vtt'),
})
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
_IE_DESC = 'ITV articles: News, British Touring Car Championship'
IE_DESC = 'ITV articles: News, British Touring Car Championship'
_TESTS = [{
'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

View File

@ -0,0 +1,97 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
urlencode_postdata,
url_or_none,
str_or_none,
)
class NamavaIE(InfoExtractor):
IE_NAME = 'namava'
_NETRC_MACHINE = IE_NAME
_VALID_URL = r'https?://(?:www\.)?play\.namava\.ir/.*\bm=(?P<id>[0-9]+)'
_TEST = {
'url': 'https://play.namava.ir/?m=52396&p=desktop',
'md5': '15639792543cc8e830a3451db1f44c72',
'info_dict': {
'id': '52396',
'ext': 'mp4',
'title': 'پلنگ صورتی - فصل ۴ قسمت ۱',
'description': 'ماجراهای سرگرم‌کننده و طنز پلنگ صورتی و اتفاقات غیرمنتظره‌ای که همیشه برای او رخ می‌دهد و او با زیرکی خاص خودش، راه‌حلی را پیدا می‌کند و...'
},
}
_LOGIN_URL = 'https://www.namava.ir/api/v1.0/accounts/by-phone/login'
HOST = 'www.namava.ir'
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
if not username:
raise ExtractorError(
'Unable to login: you have to pass username and password to logging in.',
expected=True)
login_data = {
'UserName': username,
'Password': password,
}
response = self._download_json(
self._LOGIN_URL, None,
'Logging in', data=urlencode_postdata(login_data))
if response.get('succeeded') is True:
self._set_cookie(self.HOST, 'auth_v2', response.get('result'))
return True
error = response.get('error', {})
error_message = error.get('message', '')
raise ExtractorError(
'Unable to login: %s said: %s' % (self.IE_NAME, error_message),
expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'https://www.namava.ir/api2/movie/' + video_id,
video_id, 'Fetching video info', headers={
'Accept': 'application/json, text/plain, */*',
})
title = info.get('Name')
if title is None:
raise ExtractorError(
'Unable to fetch video info',
expected=True)
media_info = info.get('MediaInfoModel', {})
domain = media_info.get('Domain') or ''
m3u8_file = media_info.get('File') or ''
m3u8_url = url_or_none(domain + m3u8_file)
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', fatal=False)
self._sort_formats(formats)
url = formats[-1]['url']
if len(formats) > 1:
url = formats[-2]['url']
result = {
'id': video_id,
'title': title,
'ext': 'mp4',
'description': str_or_none(info.get('ShortDescription')),
'formats': formats,
'thumbnail': url_or_none(info.get('ImageAbsoluteUrl')),
'url': url
}
return result

View File

@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
['arch', '', 'http://ussenate-f.akamaihd.net/']
]
_IE_NAME = 'senate.gov'
IE_NAME = 'senate.gov'
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

View File

@ -686,6 +686,8 @@ class JSInterpreter(object):
raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
def _dump(self, obj, namespace):
if obj is JS_Undefined:
return 'undefined'
try:
return json.dumps(obj)
except TypeError: