Browse Source

[subtitles] Use self._download_webpage for extracting the subtitles

It raises ExtractorError for the same exceptions we have to catch.
rtmp_test
Jaime Marquínez Ferrándiz 11 years ago
parent
commit
7fad1c6328
3 changed files with 11 additions and 18 deletions
  1. +4
    -6
      youtube_dl/extractor/dailymotion.py
  2. +3
    -9
      youtube_dl/extractor/subtitles.py
  3. +4
    -3
      youtube_dl/extractor/youtube.py

+ 4
- 6
youtube_dl/extractor/dailymotion.py View File

@ -1,14 +1,11 @@
import re
import json
import itertools
import socket
from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_http_client,
compat_urllib_error,
compat_urllib_request,
compat_str,
get_element_by_attribute,
@ -98,10 +95,11 @@ class DailymotionIE(SubtitlesInfoExtractor):
}]
def _get_available_subtitles(self, video_id):
request = compat_urllib_request.Request('https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id)
try:
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
sub_list = self._download_webpage(
'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
video_id, note=False)
except ExtractorError as err:
self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
return {}
info = json.loads(sub_list)


+ 3
- 9
youtube_dl/extractor/subtitles.py View File

@ -1,12 +1,8 @@
import socket
from .common import InfoExtractor
from ..utils import (
compat_http_client,
compat_urllib_error,
compat_urllib_request,
compat_str,
ExtractorError,
)
@ -52,8 +48,8 @@ class SubtitlesInfoExtractor(InfoExtractor):
def _request_subtitle_url(self, sub_lang, url):
""" makes the http request for the subtitle """
try:
sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
sub = self._download_webpage(url, None, note=False)
except ExtractorError as err:
self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
return
if not sub:
@ -88,5 +84,3 @@ class SubtitlesInfoExtractor(InfoExtractor):
elif self._downloader.params.get('writeautomaticsub', False):
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
return video_subtitles

+ 4
- 3
youtube_dl/extractor/youtube.py View File

@ -454,10 +454,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
return self._decrypt_signature(s)
def _get_available_subtitles(self, video_id):
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
sub_list = self._download_webpage(
'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
video_id, note=False)
except ExtractorError as err:
self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
return {}
lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)


Loading…
Cancel
Save