Browse Source

[ted] fixed error in case of no subtitles present

I created a test, but I leave it commented since TED videos get
new subtitles frequently.
rtmp_test
Ismaël Mejía 11 years ago
parent
commit
4ed3e51080
2 changed files with 22 additions and 8 deletions
  1. +6
    -0
      test/test_ted_subtitles.py
  2. +16
    -8
      youtube_dl/extractor/ted.py

+ 6
- 0
test/test_ted_subtitles.py View File

@ -51,6 +51,12 @@ class TestTedSubtitles(unittest.TestCase):
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
# def test_nosubtitles(self):
# self.DL.expect_warning(u'video doesn\'t have subtitles')
# self.url = 'http://www.ted.com/talks/rodrigo_canales_the_deadly_genius_of_drug_cartels.html'
# self.DL.params['writesubtitles'] = True
# self.DL.params['allsubtitles'] = True
# subtitles = self.getSubtitles()
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']


+ 16
- 8
youtube_dl/extractor/ted.py View File

@ -3,6 +3,11 @@ import re
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_str,
RegexNotFoundError,
)
class TEDIE(SubtitlesInfoExtractor):
_VALID_URL=r'''http://www\.ted\.com/
(
@ -105,12 +110,15 @@ class TEDIE(SubtitlesInfoExtractor):
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
try:
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
except RegexNotFoundError as err:
self._downloader.report_warning(u'video doesn\'t have subtitles')
return {}

Loading…
Cancel
Save