[ted] Added support for subtitle download
This commit is contained in:
parent
1f343eaabb
commit
a9a3876d55
2 changed files with 87 additions and 4 deletions
63
test/test_ted_subtitles.py
Normal file
63
test/test_ted_subtitles.py
Normal file
|
@ -0,0 +1,63 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import sys
|
||||
import unittest
|
||||
import hashlib
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl.extractor import TEDIE
|
||||
from youtube_dl.utils import *
|
||||
from helper import FakeYDL
|
||||
|
||||
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
|
||||
|
||||
class TestTedSubtitles(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.DL = FakeYDL()
|
||||
self.url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
|
||||
def getInfoDict(self):
|
||||
IE = TEDIE(self.DL)
|
||||
info_dict = IE.extract(self.url)
|
||||
return info_dict
|
||||
def getSubtitles(self):
|
||||
info_dict = self.getInfoDict()
|
||||
return info_dict[0]['subtitles']
|
||||
def test_no_writesubtitles(self):
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(subtitles, None)
|
||||
def test_subtitles(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d')
|
||||
def test_subtitles_lang(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['subtitleslangs'] = ['fr']
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6')
|
||||
def test_allsubtitles(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(len(subtitles.keys()), 28)
|
||||
def test_list_subtitles(self):
|
||||
self.DL.params['listsubtitles'] = True
|
||||
info_dict = self.getInfoDict()
|
||||
self.assertEqual(info_dict, [None])
|
||||
def test_automatic_captions(self):
|
||||
self.DL.params['writeautomaticsub'] = True
|
||||
self.DL.params['subtitleslang'] = ['en']
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertTrue(len(subtitles.keys()) == 0)
|
||||
def test_multiple_langs(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
langs = ['es', 'fr', 'de']
|
||||
self.DL.params['subtitleslangs'] = langs
|
||||
subtitles = self.getSubtitles()
|
||||
for lang in langs:
|
||||
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
|
@ -1,10 +1,9 @@
|
|||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .subtitles import SubtitlesInfoExtractor
|
||||
|
||||
|
||||
class TEDIE(InfoExtractor):
|
||||
class TEDIE(SubtitlesInfoExtractor):
|
||||
_VALID_URL=r'''http://www\.ted\.com/
|
||||
(
|
||||
((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
|
||||
|
@ -82,11 +81,21 @@ class TEDIE(InfoExtractor):
|
|||
'url': stream['file'],
|
||||
'format': stream['id']
|
||||
} for stream in info['htmlStreams']]
|
||||
|
||||
video_id = info['id']
|
||||
|
||||
# subtitles
|
||||
video_subtitles = self.extract_subtitles(video_id, webpage)
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
self._list_available_subtitles(video_id, webpage)
|
||||
return
|
||||
|
||||
info = {
|
||||
'id': info['id'],
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'description': desc,
|
||||
'subtitles': video_subtitles,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
@ -94,3 +103,14 @@ class TEDIE(InfoExtractor):
|
|||
info.update(info['formats'][-1])
|
||||
|
||||
return info
|
||||
|
||||
def _get_available_subtitles(self, video_id, webpage):
|
||||
options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL)
|
||||
languages = re.findall(r'(?:<option value=")(\S+)"', options)
|
||||
if languages:
|
||||
sub_lang_list = {}
|
||||
for l in languages:
|
||||
url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l)
|
||||
sub_lang_list[l] = url
|
||||
return sub_lang_list
|
||||
return {}
|
||||
|
|
Loading…
Reference in a new issue