github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

Removed conversion from youtube closed caption format to srt since youtube api supports the 'srt' format

Browse source
This commit is contained in:
Ismael Mejia 2013-02-21 20:51:35 +01:00
parent 8271226a55
commit 2e5d60b7db
2 changed files with 6 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
test/test_youtube_subtitles.py
View file

@ -43,7 +43,7 @@ def test_youtube_subtitles(self):
DL.params['writesubtitles'] = True DL.params['writesubtitles'] = True
IE = YoutubeIE(DL) IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM') info_dict = IE.extract('QRS8MkLhQmM')
self.assertEqual(md5(info_dict[0]['subtitles']), 'c3228550d59116f3c29fba370b55d033') self.assertEqual(md5(info_dict[0]['subtitles']), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_subtitles_it(self): def test_youtube_subtitles_it(self):
DL = FakeDownloader() DL = FakeDownloader()
@ -51,7 +51,7 @@ def test_youtube_subtitles_it(self):
DL.params['subtitleslang'] = 'it' DL.params['subtitleslang'] = 'it'
IE = YoutubeIE(DL) IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM') info_dict = IE.extract('QRS8MkLhQmM')
self.assertEqual(md5(info_dict[0]['subtitles']), '132a88a0daf8e1520f393eb58f1f646a') self.assertEqual(md5(info_dict[0]['subtitles']), '164a51f16f260476a05b50fe4c2f161d')
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

24
youtube_dl/InfoExtractors.py
View file

@ -228,23 +228,6 @@ def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol.""" """Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected') self._downloader.to_screen(u'[youtube] RTMP download detected')
def _closed_captions_xml_to_srt(self, xml_string):
srt = ''
texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
# TODO parse xml instead of regex
for n, (start, dur_tag, dur, caption) in enumerate(texts):
if not dur: dur = '4'
start = float(start)
end = start + float(dur)
start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
caption = unescapeHTML(caption)
caption = unescapeHTML(caption) # double cycle, intentional
srt += str(n+1) + '\n'
srt += start + ' --> ' + end + '\n'
srt += caption + '\n\n'
return srt
def _extract_subtitles(self, video_id): def _extract_subtitles(self, video_id):
self.report_video_subtitles_download(video_id) self.report_video_subtitles_download(video_id)
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
@ -268,15 +251,16 @@ def _extract_subtitles(self, video_id):
'lang': srt_lang, 'lang': srt_lang,
'name': srt_lang_list[srt_lang].encode('utf-8'), 'name': srt_lang_list[srt_lang].encode('utf-8'),
'v': video_id, 'v': video_id,
'fmt': 'srt',
}) })
url = 'http://www.youtube.com/api/timedtext?' + params url = 'http://www.youtube.com/api/timedtext?' + params
try: try:
srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8') srt = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
if not srt_xml: if not srt:
return (u'WARNING: Did not fetch video subtitles', None) return (u'WARNING: Did not fetch video subtitles', None)
return (None, self._closed_captions_xml_to_srt(srt_xml)) return (None, srt)
def _print_formats(self, formats): def _print_formats(self, formats):
print('Available formats:') print('Available formats:')