Skip to content

A feature-rich command-line audio/video downloader

[ie/tiktok] Fix extractor (#17452)

bashonlyb375e1d85c8f
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py
index 732f8b140e..5278c07bde 100644
--- a/yt_dlp/extractor/common.py
+++ b/yt_dlp/extractor/common.py
@@ -3960,6 +3960,19 @@ class InfoExtractor:
headers['Ytdl-request-proxy'] = geo_verification_proxy
return headers
+ @staticmethod
+ def _generate_blockbuster_headers(*, min_headers=2, max_headers=8):
+ """Randomize our HTTP header fingerprint in an attempt to bust HTTP Error 403 blockage"""
+
+ def random_letters(minimum, maximum):
+ # Omit vowels so we don't generate valid header names like 'authorization', etc
+ return ''.join(random.choices('bcdfghjklmnpqrstvwxz', k=random.randint(minimum, maximum)))
+
+ return {
+ random_letters(8, 24): random_letters(16, 32)
+ for _ in range(random.randint(min_headers, max_headers))
+ }
+
@staticmethod
def _generic_id(url):
return urllib.parse.unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
diff --git a/yt_dlp/extractor/dailymotion.py b/yt_dlp/extractor/dailymotion.py
index e8c8ab8b28..de56e9e276 100644
--- a/yt_dlp/extractor/dailymotion.py
+++ b/yt_dlp/extractor/dailymotion.py
@@ -1,6 +1,5 @@
import functools
import json
-import random
import re
import urllib.parse
@@ -364,19 +363,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
continue
yield update_url(player_url, query=query_string)
- @staticmethod
- def _generate_blockbuster_headers():
- """Randomize our HTTP header fingerprint to bust the HTTP Error 403 block"""
-
- def random_letters(minimum, maximum):
- # Omit vowels so we don't generate valid header names like 'authorization', etc
- return ''.join(random.choices('bcdfghjklmnpqrstvwxz', k=random.randint(minimum, maximum)))
-
- return {
- random_letters(8, 24): random_letters(16, 32)
- for _ in range(random.randint(2, 8))
- }
-
def _extract_dailymotion_m3u8_formats_and_subtitles(self, media_url, video_id, live=False):
"""See https://github.com/yt-dlp/yt-dlp/issues/15526"""
diff --git a/yt_dlp/extractor/tiktok.py b/yt_dlp/extractor/tiktok.py
index 0660e6e693..f02515c494 100644
--- a/yt_dlp/extractor/tiktok.py
+++ b/yt_dlp/extractor/tiktok.py
@@ -274,9 +274,10 @@ class TikTokBaseIE(InfoExtractor):
def _extract_web_data_and_status(self, url, video_id, fatal=True):
video_data, status = {}, -1
+ headers = self._generate_blockbuster_headers()
def get_webpage(note='Downloading webpage'):
- res = self._download_webpage_handle(url, video_id, note, fatal=fatal, impersonate=True)
+ res = self._download_webpage_handle(url, video_id, note, fatal=fatal, headers=headers)
if res is False:
return False
@@ -1155,7 +1156,7 @@ class TikTokUserIE(TikTokBaseIE):
webpage = self._download_webpage(
self._UPLOADER_URL_FORMAT % user_name, user_name,
'Downloading user webpage', 'Unable to download user webpage',
- fatal=False, impersonate=True) or ''
+ fatal=False, headers=self._generate_blockbuster_headers()) or ''
detail = traverse_obj(
self._get_universal_data(webpage, user_name), ('webapp.user-detail', {dict})) or {}
video_count = traverse_obj(detail, ('userInfo', ('stats', 'statsV2'), 'videoCount', {int}, any))
@@ -1613,7 +1614,8 @@ class TikTokLiveIE(TikTokBaseIE):
uploader, room_id = self._match_valid_url(url).group('uploader', 'id')
if not room_id:
webpage = self._download_webpage(
- format_field(uploader, None, self._UPLOADER_URL_FORMAT), uploader, impersonate=True)
+ format_field(uploader, None, self._UPLOADER_URL_FORMAT), uploader,
+ headers=self._generate_blockbuster_headers())
room_id = traverse_obj(
self._get_universal_data(webpage, uploader),
('webapp.user-detail', 'userInfo', 'user', 'roomId', {str}))