aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--youtube_dl/__init__.py1
-rw-r--r--youtube_dl/extractor/aftonbladet.py15
-rw-r--r--youtube_dl/extractor/bandcamp.py38
-rw-r--r--youtube_dl/extractor/blinkx.py30
-rw-r--r--youtube_dl/extractor/generic.py11
-rw-r--r--youtube_dl/extractor/mailru.py5
-rw-r--r--youtube_dl/extractor/ndr.py24
-rw-r--r--youtube_dl/extractor/nowness.py9
-rw-r--r--youtube_dl/version.py2
9 files changed, 64 insertions, 71 deletions
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 4e657e297..cbb053e13 100644
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -56,6 +56,7 @@ __authors__ = (
'Nicolas Évrard',
'Jason Normore',
'Hoje Lee',
+ 'Adam Thalhammer',
)
__license__ = 'Public Domain'
diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py
index 6a8cd14c9..cfc7370ae 100644
--- a/youtube_dl/extractor/aftonbladet.py
+++ b/youtube_dl/extractor/aftonbladet.py
@@ -1,7 +1,6 @@
# encoding: utf-8
from __future__ import unicode_literals
-import datetime
import re
from .common import InfoExtractor
@@ -16,6 +15,7 @@ class AftonbladetIE(InfoExtractor):
'ext': 'mp4',
'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
'description': 'Jupiters måne mest aktiv av alla himlakroppar',
+ 'timestamp': 1394142732,
'upload_date': '20140306',
},
}
@@ -27,17 +27,17 @@ class AftonbladetIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
# find internal video meta data
- META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
+ meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
internal_meta_id = self._html_search_regex(
r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
- internal_meta_url = META_URL % internal_meta_id
+ internal_meta_url = meta_url % internal_meta_id
internal_meta_json = self._download_json(
internal_meta_url, video_id, 'Downloading video meta data')
# find internal video formats
- FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
+ format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
internal_video_id = internal_meta_json['videoId']
- internal_formats_url = FORMATS_URL % internal_video_id
+ internal_formats_url = format_url % internal_video_id
internal_formats_json = self._download_json(
internal_formats_url, video_id, 'Downloading video formats')
@@ -54,16 +54,13 @@ class AftonbladetIE(InfoExtractor):
})
self._sort_formats(formats)
- timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
- upload_date = timestamp.strftime('%Y%m%d')
-
return {
'id': video_id,
'title': internal_meta_json['title'],
'formats': formats,
'thumbnail': internal_meta_json['imageUrl'],
'description': internal_meta_json['shortPreamble'],
- 'upload_date': upload_date,
+ 'timestamp': internal_meta_json['timePublished'],
'duration': internal_meta_json['duration'],
'view_count': internal_meta_json['views'],
}
diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 929aafdff..dcbbdef43 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -19,7 +19,7 @@ class BandcampIE(InfoExtractor):
'md5': 'c557841d5e50261777a6585648adf439',
'info_dict': {
"title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
- "duration": 10,
+ "duration": 9.8485,
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}]
@@ -28,36 +28,32 @@ class BandcampIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
- # We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
- if m_download is None:
+ if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
if m_trackinfo:
json_code = m_trackinfo.group(1)
- data = json.loads(json_code)
- d = data[0]
+ data = json.loads(json_code)[0]
- duration = int(round(d['duration']))
formats = []
- for format_id, format_url in d['file'].items():
- ext, _, abr_str = format_id.partition('-')
-
+ for format_id, format_url in data['file'].items():
+ ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': format_url,
- 'ext': format_id.partition('-')[0],
+ 'ext': ext,
'vcodec': 'none',
- 'acodec': format_id.partition('-')[0],
- 'abr': int(format_id.partition('-')[2]),
+ 'acodec': ext,
+ 'abr': int(abr_str),
})
self._sort_formats(formats)
return {
- 'id': compat_str(d['id']),
- 'title': d['title'],
+ 'id': compat_str(data['id']),
+ 'title': data['title'],
'formats': formats,
- 'duration': duration,
+ 'duration': float(data['duration']),
}
else:
raise ExtractorError('No free songs found')
@@ -67,11 +63,9 @@ class BandcampIE(InfoExtractor):
r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
webpage, re.MULTILINE | re.DOTALL).group('id')
- download_webpage = self._download_webpage(download_link, video_id,
- 'Downloading free downloads page')
- # We get the dictionary of the track from some javascrip code
- info = re.search(r'items: (.*?),$',
- download_webpage, re.MULTILINE).group(1)
+ download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
+ # We get the dictionary of the track from some javascript code
+ info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320']
@@ -100,7 +94,7 @@ class BandcampIE(InfoExtractor):
class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album'
- _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?'
+ _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
_TEST = {
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@@ -123,7 +117,7 @@ class BandcampAlbumIE(InfoExtractor):
'params': {
'playlistend': 2
},
- 'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
+ 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
}
def _real_extract(self, url):
diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py
index 96408e4e0..38ccd957f 100644
--- a/youtube_dl/extractor/blinkx.py
+++ b/youtube_dl/extractor/blinkx.py
@@ -1,6 +1,5 @@
from __future__ import unicode_literals
-import datetime
import json
import re
@@ -19,15 +18,16 @@ class BlinkxIE(InfoExtractor):
'file': '8aQUy7GV.mp4',
'md5': '2e9a07364af40163a908edbf10bb2492',
'info_dict': {
- "title": "Police Car Rolls Away",
- "uploader": "stupidvideos.com",
- "upload_date": "20131215",
- "description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
- "duration": 14.886,
- "thumbnails": [{
- "width": 100,
- "height": 76,
- "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
+ 'title': 'Police Car Rolls Away',
+ 'uploader': 'stupidvideos.com',
+ 'upload_date': '20131215',
+ 'timestamp': 1387068000,
+ 'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
+ 'duration': 14.886,
+ 'thumbnails': [{
+ 'width': 100,
+ 'height': 76,
+ 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
}],
},
}
@@ -41,9 +41,6 @@ class BlinkxIE(InfoExtractor):
'video=%s' % video_id)
data_json = self._download_webpage(api_url, display_id)
data = json.loads(data_json)['api']['results'][0]
- dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
- pload_date = dt.strftime('%Y%m%d')
-
duration = None
thumbnails = []
formats = []
@@ -64,10 +61,7 @@ class BlinkxIE(InfoExtractor):
vcodec = remove_start(m['vcodec'], 'ff')
acodec = remove_start(m['acodec'], 'ff')
tbr = (int(m['vbr']) + int(m['abr'])) // 1000
- format_id = (u'%s-%sk-%s' %
- (vcodec,
- tbr,
- m['w']))
+ format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w'])
formats.append({
'format_id': format_id,
'url': m['link'],
@@ -88,7 +82,7 @@ class BlinkxIE(InfoExtractor):
'title': data['title'],
'formats': formats,
'uploader': data['channel_name'],
- 'upload_date': pload_date,
+ 'timestamp': data['pubdate_epoch'],
'description': data.get('description'),
'thumbnails': thumbnails,
'duration': duration,
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 286133282..38a357d3b 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -363,8 +363,13 @@ class GenericIE(InfoExtractor):
return self.url_result('http://' + url)
else:
if default_search == 'auto_warning':
- self._downloader.report_warning(
- 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url)
+ if re.match(r'^(?:url|URL)$', url):
+ raise ExtractorError(
+ 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
+ expected=True)
+ else:
+ self._downloader.report_warning(
+ 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url)
return self.url_result('ytsearch:' + url)
else:
assert ':' in default_search
@@ -560,7 +565,7 @@ class GenericIE(InfoExtractor):
# Look for embedded NovaMov-based player
mobj = re.search(
- r'''(?x)<iframe[^>]+?src=(["\'])
+ r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
(?P<url>http://(?:(?:embed|www)\.)?
(?:novamov\.com|
nowvideo\.(?:ch|sx|eu|at|ag|co)|
diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py
index f819c09b3..5016989cc 100644
--- a/youtube_dl/extractor/mailru.py
+++ b/youtube_dl/extractor/mailru.py
@@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
-import datetime
from .common import InfoExtractor
@@ -19,6 +18,7 @@ class MailRuIE(InfoExtractor):
'id': '46301138',
'ext': 'mp4',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
+ 'timestamp': 1393232740,
'upload_date': '20140224',
'uploader': 'sonypicturesrus',
'uploader_id': 'sonypicturesrus@mail.ru',
@@ -43,7 +43,6 @@ class MailRuIE(InfoExtractor):
thumbnail = movie['poster']
duration = movie['duration']
- upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d')
view_count = video_data['views_count']
formats = [
@@ -57,7 +56,7 @@ class MailRuIE(InfoExtractor):
'id': content_id,
'title': title,
'thumbnail': thumbnail,
- 'upload_date': upload_date,
+ 'timestamp': video_data['timestamp'],
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py
index 0650f9564..53b34f5e6 100644
--- a/youtube_dl/extractor/ndr.py
+++ b/youtube_dl/extractor/ndr.py
@@ -4,7 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+)
class NDRIE(InfoExtractor):
@@ -45,13 +48,12 @@ class NDRIE(InfoExtractor):
page = self._download_webpage(url, video_id, 'Downloading page')
- title = self._og_search_title(page)
+ title = self._og_search_title(page).strip()
description = self._og_search_description(page)
+ if description:
+ description = description.strip()
- mobj = re.search(
- r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
- page)
- duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+ duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
formats = []
@@ -66,10 +68,12 @@ class NDRIE(InfoExtractor):
video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
if video_url:
- thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
- page, 'thumbnail', fatal=False)
- if thumbnail:
- thumbnail = 'http://www.ndr.de' + thumbnail
+ thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
+ if thumbnails:
+ QUALITIES = ['xs', 's', 'm', 'l', 'xl']
+ thumbnails.sort(key=lambda thumb: QUALITIES.index(thumb[1]) if thumb[1] in QUALITIES else -1)
+ thumbnail = 'http://www.ndr.de' + thumbnails[-1][0]
+
for format_id in ['lo', 'hi', 'hq']:
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py
index b1bcb7e54..1c5e9401f 100644
--- a/youtube_dl/extractor/nowness.py
+++ b/youtube_dl/extractor/nowness.py
@@ -4,9 +4,7 @@ import re
from .brightcove import BrightcoveIE
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
-)
+from ..utils import ExtractorError
class NownessIE(InfoExtractor):
@@ -14,9 +12,10 @@ class NownessIE(InfoExtractor):
_TEST = {
'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
- 'file': '2520295746001.mp4',
- 'md5': '0ece2f70a7bd252c7b00f3070182d418',
+ 'md5': '068bc0202558c2e391924cb8cc470676',
'info_dict': {
+ 'id': '2520295746001',
+ 'ext': 'mp4',
'description': 'Candor: The Art of Gesticulation',
'uploader': 'Nowness',
'title': 'Candor: The Art of Gesticulation',
diff --git a/youtube_dl/version.py b/youtube_dl/version.py
index 3193fd152..638ff8af5 100644
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,2 +1,2 @@
-__version__ = '2014.05.17'
+__version__ = '2014.05.19'