-# coding: utf-8
-from __future__ import unicode_literals
-
+import base64
import codecs
+import datetime as dt
+import hashlib
+import hmac
+import json
+import random
import re
from .common import InfoExtractor
-from ..compat import (
- compat_chr,
- compat_ord,
- compat_urllib_parse_unquote,
-)
+from ..compat import compat_ord, compat_urllib_parse_unquote
from ..utils import (
ExtractorError,
float_or_none,
merge_dicts,
multipart_encode,
parse_duration,
- random_birthday,
+ traverse_obj,
+ try_call,
+ try_get,
urljoin,
)
class CDAIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
- _BASE_URL = 'http://www.cda.pl/'
+ _NETRC_MACHINE = 'cdapl'
+
+ _BASE_URL = 'https://www.cda.pl'
+ _BASE_API_URL = 'https://api.cda.pl'
+ _API_HEADERS = {
+ 'Accept': 'application/vnd.cda.public+json',
+ }
+ # hardcoded in the app
+ _LOGIN_REQUEST_AUTH = 'Basic YzU3YzBlZDUtYTIzOC00MWQwLWI2NjQtNmZmMWMxY2Y2YzVlOklBTm95QlhRRVR6U09MV1hnV3MwMW0xT2VyNWJNZzV4clRNTXhpNGZJUGVGZ0lWUlo5UGVYTDhtUGZaR1U1U3Q'
+ _BEARER_CACHE = 'cda-bearer'
+
_TESTS = [{
'url': 'http://www.cda.pl/video/5749950c',
'md5': '6f844bf51b15f31fae165365707ae970',
'average_rating': float,
'duration': 39,
'age_limit': 0,
+ 'upload_date': '20160221',
+ 'timestamp': 1456078244,
}
}, {
'url': 'http://www.cda.pl/video/57413289',
'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'crash404',
- 'view_count': int,
'average_rating': float,
'duration': 137,
'age_limit': 0,
+ 'upload_date': '20160220',
+ 'timestamp': 1455968218,
}
}, {
- # Age-restricted
- 'url': 'http://www.cda.pl/video/1273454c4',
+ # Age-restricted with vfilm redirection
+ 'url': 'https://www.cda.pl/video/8753244c4',
+ 'md5': 'd8eeb83d63611289507010d3df3bb8b3',
'info_dict': {
- 'id': '1273454c4',
+ 'id': '8753244c4',
'ext': 'mp4',
- 'title': 'Bronson (2008) napisy HD 1080p',
- 'description': 'md5:1b6cb18508daf2dc4e0fa4db77fec24c',
+ 'title': '[18+] Bez Filtra: Rezerwowe Psy czyli... najwulgarniejsza polska gra?',
+ 'description': 'md5:ae80bac31bd6a9f077a6cce03c7c077e',
'height': 1080,
- 'uploader': 'boniek61',
+ 'uploader': 'arhn eu',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'duration': 991,
+ 'age_limit': 18,
+ 'average_rating': float,
+ 'timestamp': 1633888264,
+ 'upload_date': '20211010',
+ }
+ }, {
+ # Age-restricted without vfilm redirection
+ 'url': 'https://www.cda.pl/video/17028157b8',
+ 'md5': 'c1fe5ff4582bace95d4f0ce0fbd0f992',
+ 'info_dict': {
+ 'id': '17028157b8',
+ 'ext': 'mp4',
+ 'title': 'STENDUPY MICHAŁ OGIŃSKI',
+ 'description': 'md5:5851f3272bfc31f762d616040a1d609a',
+ 'height': 480,
+ 'uploader': 'oginski',
'thumbnail': r're:^https?://.*\.jpg$',
- 'duration': 5554,
+ 'duration': 18855,
'age_limit': 18,
- 'view_count': int,
'average_rating': float,
- },
+ 'timestamp': 1699705901,
+ 'upload_date': '20231111',
+ }
}, {
'url': 'http://ebd.cda.pl/0x0/5749950c',
'only_matching': True,
}]
def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
- form_data = random_birthday('rok', 'miesiac', 'dzien')
- form_data.update({'return': url, 'module': 'video', 'module_id': video_id})
- data, content_type = multipart_encode(form_data)
+ data, content_type = multipart_encode({'age_confirm': ''})
return self._download_webpage(
- urljoin(url, '/a/validatebirth'), video_id, *args,
+ url, video_id, *args,
data=data, headers={
'Referer': url,
'Content-Type': content_type,
}, **kwargs)
+ def _perform_login(self, username, password):
+ app_version = random.choice((
+ '1.2.88 build 15306',
+ '1.2.174 build 18469',
+ ))
+ android_version = random.randrange(8, 14)
+ phone_model = random.choice((
+ # x-kom.pl top selling Android smartphones, as of 2022-12-26
+ # https://www.x-kom.pl/g-4/c/1590-smartfony-i-telefony.html?f201-system-operacyjny=61322-android
+ 'ASUS ZenFone 8',
+ 'Motorola edge 20 5G',
+ 'Motorola edge 30 neo 5G',
+ 'Motorola moto g22',
+ 'OnePlus Nord 2T 5G',
+ 'Samsung Galaxy A32 SM‑A325F',
+ 'Samsung Galaxy M13',
+ 'Samsung Galaxy S20 FE 5G',
+ 'Xiaomi 11T',
+ 'Xiaomi POCO M4 Pro',
+ 'Xiaomi Redmi 10',
+ 'Xiaomi Redmi 10C',
+ 'Xiaomi Redmi 9C NFC',
+ 'Xiaomi Redmi Note 10 Pro',
+ 'Xiaomi Redmi Note 11 Pro',
+ 'Xiaomi Redmi Note 11',
+ 'Xiaomi Redmi Note 11S 5G',
+ 'Xiaomi Redmi Note 11S',
+ 'realme 10',
+ 'realme 9 Pro+',
+ 'vivo Y33s',
+ ))
+ self._API_HEADERS['User-Agent'] = f'pl.cda 1.0 (version {app_version}; Android {android_version}; {phone_model})'
+
+ cached_bearer = self.cache.load(self._BEARER_CACHE, username) or {}
+ if cached_bearer.get('valid_until', 0) > dt.datetime.now().timestamp() + 5:
+ self._API_HEADERS['Authorization'] = f'Bearer {cached_bearer["token"]}'
+ return
+
+ password_hash = base64.urlsafe_b64encode(hmac.new(
+ b's01m1Oer5IANoyBXQETzSOLWXgWs01m1Oer5bMg5xrTMMxRZ9Pi4fIPeFgIVRZ9PeXL8mPfXQETZGUAN5StRZ9P',
+ ''.join(f'{bytes((bt & 255, )).hex():0>2}'
+ for bt in hashlib.md5(password.encode()).digest()).encode(),
+ hashlib.sha256).digest()).decode().replace('=', '')
+
+ token_res = self._download_json(
+ f'{self._BASE_API_URL}/oauth/token', None, 'Logging in', data=b'',
+ headers={**self._API_HEADERS, 'Authorization': self._LOGIN_REQUEST_AUTH},
+ query={
+ 'grant_type': 'password',
+ 'login': username,
+ 'password': password_hash,
+ })
+ self.cache.store(self._BEARER_CACHE, username, {
+ 'token': token_res['access_token'],
+ 'valid_until': token_res['expires_in'] + dt.datetime.now().timestamp(),
+ })
+ self._API_HEADERS['Authorization'] = f'Bearer {token_res["access_token"]}'
+
def _real_extract(self, url):
video_id = self._match_id(url)
+
+ if 'Authorization' in self._API_HEADERS:
+ return self._api_extract(video_id)
+ else:
+ return self._web_extract(video_id)
+
+ def _api_extract(self, video_id):
+ meta = self._download_json(
+ f'{self._BASE_API_URL}/video/{video_id}', video_id, headers=self._API_HEADERS)['video']
+
+ uploader = traverse_obj(meta, 'author', 'login')
+
+ formats = [{
+ 'url': quality['file'],
+ 'format': quality.get('title'),
+ 'resolution': quality.get('name'),
+ 'height': try_call(lambda: int(quality['name'][:-1])),
+ 'filesize': quality.get('length'),
+ } for quality in meta['qualities'] if quality.get('file')]
+
+ if meta.get('premium') and not meta.get('premium_free') and not formats:
+ raise ExtractorError(
+ 'Video requires CDA Premium - subscription needed', expected=True)
+
+ return {
+ 'id': video_id,
+ 'title': meta.get('title'),
+ 'description': meta.get('description'),
+ 'uploader': None if uploader == 'anonim' else uploader,
+ 'average_rating': float_or_none(meta.get('rating')),
+ 'thumbnail': meta.get('thumb'),
+ 'formats': formats,
+ 'duration': meta.get('duration'),
+ 'age_limit': 18 if meta.get('for_adults') else 0,
+ 'view_count': meta.get('views'),
+ }
+
+ def _web_extract(self, video_id):
self._set_cookie('cda.pl', 'cda.player', 'html5')
- webpage = self._download_webpage(
- self._BASE_URL + '/video/' + video_id, video_id)
+ webpage, urlh = self._download_webpage_handle(
+ f'{self._BASE_URL}/video/{video_id}/vfilm', video_id)
if 'Ten film jest dostępny dla użytkowników premium' in webpage:
- raise ExtractorError('This video is only available for premium users.', expected=True)
+ self.raise_login_required('This video is only available for premium users')
if re.search(r'niedostępn[ey] w(?: |\s+)Twoim kraju\s*<', webpage):
self.raise_geo_restricted()
need_confirm_age = False
- if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
+ if self._html_search_regex(r'(<button[^>]+name="[^"]*age_confirm[^"]*")',
webpage, 'birthday validate form', default=None):
webpage = self._download_age_confirm_page(
- url, video_id, note='Confirming age')
+ urlh.url, video_id, note='Confirming age')
need_confirm_age = True
formats = []
(?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
<(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
''', webpage, 'uploader', default=None, group='uploader')
- view_count = self._search_regex(
- r'Odsłony:(?:\s| )*([0-9]+)', webpage,
- 'view_count', default=None)
average_rating = self._search_regex(
(r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
r'<span[^>]+\bclass=["\']rating["\'][^>]*>(?P<rating_value>[0-9.]+)'), webpage, 'rating', fatal=False,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'uploader': uploader,
- 'view_count': int_or_none(view_count),
'average_rating': float_or_none(average_rating),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
b = []
for c in a:
f = compat_ord(c)
- b.append(compat_chr(33 + (f + 14) % 94) if 33 <= f and 126 >= f else compat_chr(f))
+ b.append(chr(33 + (f + 14) % 94) if 33 <= f <= 126 else chr(f))
a = ''.join(b)
a = a.replace('.cda.mp4', '')
for p in ('.2cda.pl', '.3cda.pl'):
video['file'] = video['file'].replace('adc.mp4', '.mp4')
elif not video['file'].startswith('http'):
video['file'] = decrypt_file(video['file'])
- f = {
+ video_quality = video.get('quality')
+ qualities = video.get('qualities', {})
+ video_quality = next((k for k, v in qualities.items() if v == video_quality), video_quality)
+ info_dict['formats'].append({
'url': video['file'],
- }
- m = re.search(
- r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
- page)
- if m:
- f.update({
- 'format_id': m.group('format_id'),
- 'height': int(m.group('height')),
- })
- info_dict['formats'].append(f)
+ 'format_id': video_quality,
+ 'height': int_or_none(video_quality[:-1]),
+ })
+ for quality, cda_quality in qualities.items():
+ if quality == video_quality:
+ continue
+ data = {'jsonrpc': '2.0', 'method': 'videoGetLink', 'id': 2,
+ 'params': [video_id, cda_quality, video.get('ts'), video.get('hash2'), {}]}
+ data = json.dumps(data).encode('utf-8')
+ video_url = self._download_json(
+ f'https://www.cda.pl/video/{video_id}', video_id, headers={
+ 'Content-Type': 'application/json',
+ 'X-Requested-With': 'XMLHttpRequest'
+ }, data=data, note=f'Fetching {quality} url',
+ errnote=f'Failed to fetch {quality} url', fatal=False)
+ if try_get(video_url, lambda x: x['result']['status']) == 'ok':
+ video_url = try_get(video_url, lambda x: x['result']['resp'])
+ info_dict['formats'].append({
+ 'url': video_url,
+ 'format_id': quality,
+ 'height': int_or_none(quality[:-1])
+ })
+
if not info_dict['duration']:
info_dict['duration'] = parse_duration(video.get('duration'))
extract_format(webpage, resolution)
- self._sort_formats(formats)
-
return merge_dicts(info_dict, info)