diff options
Diffstat (limited to 'yt_dlp/extractor/archiveorg.py')
| -rw-r--r-- | yt_dlp/extractor/archiveorg.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/yt_dlp/extractor/archiveorg.py b/yt_dlp/extractor/archiveorg.py index 2a25c0713..2ab3c1beb 100644 --- a/yt_dlp/extractor/archiveorg.py +++ b/yt_dlp/extractor/archiveorg.py @@ -457,7 +457,7 @@ class YoutubeWebArchiveIE(InfoExtractor): _OLDEST_CAPTURE_DATE = 20050214000000 _NEWEST_CAPTURE_DATE = 20500101000000 - def _call_cdx_api(self, item_id, url, filters: list = None, collapse: list = None, query: dict = None, note='Downloading CDX API JSON'): + def _call_cdx_api(self, item_id, url, filters: list = None, collapse: list = None, query: dict = None, note=None, fatal=False): # CDX docs: https://github.com/internetarchive/wayback/blob/master/wayback-cdx-server/README.md query = { 'url': url, @@ -468,7 +468,9 @@ class YoutubeWebArchiveIE(InfoExtractor): 'collapse': collapse or [], **(query or {}) } - res = self._download_json('https://web.archive.org/cdx/search/cdx', item_id, note, query=query) + res = self._download_json( + 'https://web.archive.org/cdx/search/cdx', item_id, + note or 'Downloading CDX API JSON', query=query, fatal=fatal) if isinstance(res, list) and len(res) >= 2: # format response to make it easier to use return list(dict(zip(res[0], v)) for v in res[1:]) @@ -481,8 +483,7 @@ class YoutubeWebArchiveIE(InfoExtractor): regex), webpage, name, default='{}'), video_id, fatal=False) def _extract_webpage_title(self, webpage): - page_title = self._html_search_regex( - r'<title>([^<]*)</title>', webpage, 'title', default='') + page_title = self._html_extract_title(webpage, default='') # YouTube video pages appear to always have either 'YouTube -' as prefix or '- YouTube' as suffix. return self._html_search_regex( r'(?:YouTube\s*-\s*(.*)$)|(?:(.*)\s*-\s*YouTube$)', |