pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-02 16:37:59 +09:00
Code Issues Projects Releases Wiki Activity

[tagesschau] fix deprecation warning about inline regex flags

Browse Source 
The warning during test_download:

    DeprecationWarning: Flags not at the start of the expression '(?s)<p[^>]+class="in' (truncated)
This commit is contained in:
memo 2021-03-13 11:58:07 +01:00
parent 74bb98431e
commit 2a0d9305f4
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
youtube_dl/extractor/tagesschau.py
View File

@ -380,13 +380,13 @@ class TagesschauIE(InfoExtractor):
# Some old pages still use the old format, so we keep the previous # Some old pages still use the old format, so we keep the previous
# extractor for now. # extractor for now.
def _legacy_extract(self, webpage, display_id, title, webpage_type): def _legacy_extract(self, webpage, display_id, title, webpage_type):
DOWNLOAD_REGEX = r'(?s)<p>Wir bieten dieses (?P<kind>Video|Audio) in folgenden Formaten zum Download an:</p>\s*<div class="controls">(?P<links>.*?)</div>\s*<p>' DOWNLOAD_REGEX = r'<p>Wir bieten dieses (?P<kind>Video|Audio) in folgenden Formaten zum Download an:</p>\s*<div class="controls">(?P<links>.*?)</div>\s*<p>'
if webpage_type == 'website': # Article if webpage_type == 'website': # Article
entries = [] entries = []
for num, (entry_title, media_kind, download_text) in enumerate(re.findall( for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
r'(?s)<p[^>]+class="infotext"[^>]*>\s*(?:<a[^>]+>)?\s*<strong>(.+?)</strong>.*?</p>.*?%s' % DOWNLOAD_REGEX, r'<p[^>]+class="infotext"[^>]*>\s*(?:<a[^>]+>)?\s*<strong>(.+?)</strong>.*?</p>.*?%s' % DOWNLOAD_REGEX,
webpage), 1): webpage, flags=re.S), 1):
entries.append({ entries.append({
'id': '%s-%d' % (display_id, num), 'id': '%s-%d' % (display_id, num),
'title': '%s' % entry_title, 'title': '%s' % entry_title,
@ -397,9 +397,9 @@ class TagesschauIE(InfoExtractor):
formats = entries[0]['formats'] formats = entries[0]['formats']
else: # Assume single video else: # Assume single video
download_text = self._search_regex( download_text = self._search_regex(
DOWNLOAD_REGEX, webpage, 'download links', group='links') DOWNLOAD_REGEX, webpage, 'download links', flags=re.S, group='links')
media_kind = self._search_regex( media_kind = self._search_regex(
DOWNLOAD_REGEX, webpage, 'media kind', default='Video', group='kind') DOWNLOAD_REGEX, webpage, 'media kind', default='Video', flags=re.S, group='kind')
formats = self._legacy_extract_formats(download_text, media_kind) formats = self._legacy_extract_formats(download_text, media_kind)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
description = self._html_search_regex( description = self._html_search_regex(