commit 71e7da653382b38d8cecde20d60f722417f1cf93
parent b1b0b1ca3030a2b04dd94ec28d5ece3fda88a282
Author: Philipp Hagemeister <phihag@phihag.de>
Date: Sun, 25 Jan 2015 21:39:50 +0100
Merge branch 'master' of github.com:rg3/youtube-dl
Diffstat:
5 files changed, 35 insertions(+), 20 deletions(-)
diff --git a/AUTHORS b/AUTHORS
@@ -105,3 +105,4 @@ Dinesh S
Johan K. Jensen
Yen Chi Hsuan
Enam Mijbah Noor
+David Luhmer
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -14,6 +14,7 @@ import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
+ compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse_urlparse,
@@ -26,6 +27,7 @@ from ..utils import (
compiled_regex_type,
ExtractorError,
float_or_none,
+ HEADRequest,
int_or_none,
RegexNotFoundError,
sanitize_filename,
@@ -716,6 +718,27 @@ class InfoExtractor(object):
)
formats.sort(key=_formats_key)
+ def _check_formats(self, formats, video_id):
+ if formats:
+ formats[:] = filter(
+ lambda f: self._is_valid_url(
+ f['url'], video_id,
+ item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
+ formats)
+
+ def _is_valid_url(self, url, video_id, item='video'):
+ try:
+ self._request_webpage(
+ HEADRequest(url), video_id,
+ 'Checking %s URL' % item)
+ return True
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError):
+ self.report_warning(
+ '%s URL is invalid, skipping' % item, video_id)
+ return False
+ raise
+
def http_scheme(self):
""" Either "http:" or "https:", depending on the user's preferences """
return (
diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py
@@ -48,14 +48,20 @@ class DRTVIE(SubtitlesInfoExtractor):
elif asset['Kind'] == 'VideoResource':
duration = asset['DurationInMilliseconds'] / 1000.0
restricted_to_denmark = asset['RestrictedToDenmark']
+ spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
for link in asset['Links']:
target = link['Target']
uri = link['Uri']
+ format_id = target
+ preference = -1 if target == 'HDS' else -2
+ if spoken_subtitles:
+ preference -= 2
+ format_id += '-spoken-subtitles'
formats.append({
'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
- 'format_id': target,
+ 'format_id': format_id,
'ext': link['FileFormat'],
- 'preference': -1 if target == 'HDS' else -2,
+ 'preference': preference,
})
subtitles_list = asset.get('SubtitlesList')
if isinstance(subtitles_list, list):
diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
@@ -85,6 +85,7 @@ class LyndaIE(SubtitlesInfoExtractor):
} for format_id, video_url in prioritized_streams['0'].items()
])
+ self._check_formats(formats, video_id)
self._sort_formats(formats)
if self._downloader.params.get('listsubtitles', False):
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
@@ -4,14 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..compat import (
- compat_urlparse,
- compat_HTTPError,
-)
-from ..utils import (
- HEADRequest,
- ExtractorError,
-)
+from ..compat import compat_urlparse
from .spiegeltv import SpiegeltvIE
@@ -72,16 +65,6 @@ class SpiegelIE(InfoExtractor):
if n.tag.startswith('type') and n.tag != 'type6':
format_id = n.tag.rpartition('type')[2]
video_url = base_url + n.find('./filename').text
- # Test video URLs beforehand as some of them are invalid
- try:
- self._request_webpage(
- HEADRequest(video_url), video_id,
- 'Checking %s video URL' % format_id)
- except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
- self.report_warning(
- '%s video URL is invalid, skipping' % format_id, video_id)
- continue
formats.append({
'format_id': format_id,
'url': video_url,
@@ -94,6 +77,7 @@ class SpiegelIE(InfoExtractor):
})
duration = float(idoc[0].findall('./duration')[0].text)
+ self._check_formats(formats, video_id)
self._sort_formats(formats)
return {
