From 3c7a2762343280d0e749acffd0edcf72fa4d0661 Mon Sep 17 00:00:00 2001 From: Lesmiscore Date: Fri, 2 Sep 2022 15:51:12 +0900 Subject: [PATCH] [extractor/amazonstore] Retry to avoid captcha page (#4811) Authored by: Lesmiscore --- yt_dlp/extractor/amazon.py | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/amazon.py b/yt_dlp/extractor/amazon.py index de4917adc..56a8d844a 100644 --- a/yt_dlp/extractor/amazon.py +++ b/yt_dlp/extractor/amazon.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ExtractorError, int_or_none class AmazonStoreIE(InfoExtractor): @@ -38,8 +38,14 @@ class AmazonStoreIE(InfoExtractor): def _real_extract(self, url): id = self._match_id(url) - webpage = self._download_webpage(url, id) - data_json = self._parse_json(self._html_search_regex(r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'(.*)\'\)', webpage, 'data'), id) + + for retry in self.RetryManager(fatal=True): + webpage = self._download_webpage(url, id) + try: + data_json = self._parse_json(self._html_search_regex(r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'(.*)\'\)', webpage, 'data'), id) + except ExtractorError as e: + retry.error = e + entries = [{ 'id': video['marketPlaceID'], 'url': video['url'],