github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[Bilibili] Add subtitle converter (#1144)

Browse source 
Closes #1015
Based on https://github.com/y2361547758/bcc2ass
Authored by: u-spec-png
This commit is contained in:
u-spec-png 2021-10-04 18:37:05 +00:00 committed by GitHub
parent b11c04a8ae
commit efc947fb3e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
yt_dlp/extractor/bilibili.py
View file

@ -22,6 +22,7 @@
parse_iso8601, parse_iso8601,
try_get, try_get,
smuggle_url, smuggle_url,
srt_subtitles_timecode,
str_or_none, str_or_none,
str_to_int, str_to_int,
strip_jsonp, strip_jsonp,
@ -623,7 +624,7 @@ def _get_n_results(self, query, n):
while True: while True:
pageNumber += 1 pageNumber += 1
# FIXME # FIXME
api_url = "https://api.bilibili.com/x/web-interface/search/type?context=&page=%s&order=pubdate&keyword=%s&duration=0&tids_2=&__refresh__=true&search_type=video&tids=0&highlight=1" % (pageNumber, query) api_url = 'https://api.bilibili.com/x/web-interface/search/type?context=&page=%s&order=pubdate&keyword=%s&duration=0&tids_2=&__refresh__=true&search_type=video&tids=0&highlight=1' % (pageNumber, query)
json_str = self._download_webpage( json_str = self._download_webpage(
api_url, "None", query={"Search_key": query}, api_url, "None", query={"Search_key": query},
note='Extracting results from page %s' % pageNumber) note='Extracting results from page %s' % pageNumber)
@ -783,6 +784,12 @@ class BiliIntlBaseIE(InfoExtractor):
def _call_api(self, type, endpoint, id): def _call_api(self, type, endpoint, id):
return self._download_json(self._API_URL.format(type, endpoint), id)['data'] return self._download_json(self._API_URL.format(type, endpoint), id)['data']
def json2srt(self, json):
data = '\n\n'.join(
f'{i + 1}\n{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n{line["content"]}'
for i, line in enumerate(json['body']))
return data
def _get_subtitles(self, type, ep_id): def _get_subtitles(self, type, ep_id):
sub_json = self._call_api(type, f'/m/subtitle?ep_id={ep_id}&platform=web', ep_id) sub_json = self._call_api(type, f'/m/subtitle?ep_id={ep_id}&platform=web', ep_id)
subtitles = {} subtitles = {}
@ -790,8 +797,13 @@ def _get_subtitles(self, type, ep_id):
sub_url = sub.get('url') sub_url = sub.get('url')
if not sub_url: if not sub_url:
continue continue
sub_data = self._download_json(sub_url, ep_id, fatal=False)
if not sub_data:
continue
sub_data = self._parse_json(sub_data)
subtitles.setdefault(sub.get('key', 'en'), []).append({ subtitles.setdefault(sub.get('key', 'en'), []).append({
'url': sub_url, 'ext': 'srt',
'data': self.json2srt(sub_data)
}) })
return subtitles return subtitles