Skip to content

A feature-rich command-line audio/video downloader

[ie/telecinco] Fix extractor (#13379)

bashonly03dba2012d9b
diff --git a/yt_dlp/extractor/mitele.py b/yt_dlp/extractor/mitele.py
index 55fa83b51f..0dded38c65 100644
--- a/yt_dlp/extractor/mitele.py
+++ b/yt_dlp/extractor/mitele.py
@@ -1,7 +1,5 @@
from .telecinco import TelecincoBaseIE
-from ..networking.exceptions import HTTPError
from ..utils import (
- ExtractorError,
int_or_none,
parse_iso8601,
)
@@ -81,17 +79,7 @@ class MiTeleIE(TelecincoBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
-
- try: # yt-dlp's default user-agents are too old and blocked by akamai
- webpage = self._download_webpage(url, display_id, headers={
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
- })
- except ExtractorError as e:
- if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
- raise
- # Retry with impersonation if hardcoded UA is insufficient to bypass akamai
- webpage = self._download_webpage(url, display_id, impersonate=True)
-
+ webpage = self._download_akamai_webpage(url, display_id)
pre_player = self._search_json(
r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=',
webpage, 'Pre Player', display_id)['prePlayer']
diff --git a/yt_dlp/extractor/telecinco.py b/yt_dlp/extractor/telecinco.py
index a34f2afd4a..2dbe2a7768 100644
--- a/yt_dlp/extractor/telecinco.py
+++ b/yt_dlp/extractor/telecinco.py
@@ -63,6 +63,17 @@ class TelecincoBaseIE(InfoExtractor):
'http_headers': headers,
}
+ def _download_akamai_webpage(self, url, display_id):
+ try: # yt-dlp's default user-agents are too old and blocked by akamai
+ return self._download_webpage(url, display_id, headers={
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
+ })
+ except ExtractorError as e:
+ if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
+ raise
+ # Retry with impersonation if hardcoded UA is insufficient to bypass akamai
+ return self._download_webpage(url, display_id, impersonate=True)
+
class TelecincoIE(TelecincoBaseIE):
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
@@ -140,7 +151,7 @@ class TelecincoIE(TelecincoBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
- webpage = self._download_webpage(url, display_id)
+ webpage = self._download_akamai_webpage(url, display_id)
article = self._search_json(
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
webpage, 'article', display_id)['article']