diff --git a/Makefile b/Makefile
index 85dacfa4c..c6d09932b 100644
--- a/Makefile
+++ b/Makefile
@@ -13,13 +13,13 @@ PYTHON=/usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
ifeq ($(PREFIX),/usr)
- SYSCONFDIR=/etc
+ SYSCONFDIR=/etc
else
- ifeq ($(PREFIX),/usr/local)
- SYSCONFDIR=/etc
- else
- SYSCONFDIR=$(PREFIX)/etc
- endif
+ ifeq ($(PREFIX),/usr/local)
+ SYSCONFDIR=/etc
+ else
+ SYSCONFDIR=$(PREFIX)/etc
+ endif
endif
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
@@ -71,6 +71,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
--exclude '*~' \
--exclude '__pycache' \
--exclude '.git' \
+ --exclude 'testdata' \
-- \
bin devscripts test youtube_dl \
CHANGELOG LICENSE README.md README.txt \
diff --git a/README.md b/README.md
index 8824daee2..6dae0a580 100644
--- a/README.md
+++ b/README.md
@@ -57,9 +57,10 @@ which means you can modify it, redistribute it or use it however you like.
file. Record all downloaded videos in it.
## Download Options:
- -r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m)
+ -r, --rate-limit LIMIT maximum download rate in bytes per second (e.g.
+ 50K or 4.2M)
-R, --retries RETRIES number of retries (default is 10)
- --buffer-size SIZE size of download buffer (e.g. 1024 or 16k)
+ --buffer-size SIZE size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer do not automatically adjust the buffer size. By
default, the buffer size is automatically resized
@@ -100,6 +101,7 @@ which means you can modify it, redistribute it or use it however you like.
file modification time
--write-description write video description to a .description file
--write-info-json write video metadata to a .info.json file
+ --write-annotations write video annotations to a .annotation file
--write-thumbnail write thumbnail image to disk
## Verbosity / Simulation Options:
@@ -166,6 +168,7 @@ which means you can modify it, redistribute it or use it however you like.
processed files are overwritten by default
--embed-subs embed subtitles in the video (only for mp4
videos)
+ --add-metadata add metadata to the files
# CONFIGURATION
diff --git a/devscripts/gh-pages/update-sites.py b/devscripts/gh-pages/update-sites.py
index 33f242480..153e15c8a 100755
--- a/devscripts/gh-pages/update-sites.py
+++ b/devscripts/gh-pages/update-sites.py
@@ -16,10 +16,11 @@ def main():
ie_htmls = []
for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
ie_html = '{}'.format(ie.IE_NAME)
- try:
+ ie_desc = getattr(ie, 'IE_DESC', None)
+ if ie_desc is False:
+ continue
+ elif ie_desc is not None:
ie_html += ': {}'.format(ie.IE_DESC)
- except AttributeError:
- pass
if ie.working() == False:
ie_html += ' (Currently broken)'
ie_htmls.append('{}'.format(ie_html))
diff --git a/test/__init__.py b/test/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/helper.py b/test/helper.py
index ad1b74dd3..79a0ede48 100644
--- a/test/helper.py
+++ b/test/helper.py
@@ -1,22 +1,27 @@
import errno
import io
+import hashlib
import json
import os.path
import re
import types
import youtube_dl.extractor
-from youtube_dl import YoutubeDL, YoutubeDLHandler
-from youtube_dl.utils import (
- compat_cookiejar,
- compat_urllib_request,
-)
+from youtube_dl import YoutubeDL
-youtube_dl._setup_opener(timeout=10)
-PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
-with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
- parameters = json.load(pf)
+def global_setup():
+ youtube_dl._setup_opener(timeout=10)
+
+
+def get_params(override=None):
+ PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
+ "parameters.json")
+ with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+ parameters = json.load(pf)
+ if override:
+ parameters.update(override)
+ return parameters
def try_rm(filename):
@@ -32,7 +37,7 @@ class FakeYDL(YoutubeDL):
def __init__(self):
# Different instances of the downloader can't share the same dictionary
# some test set the "sublang" parameter, which would break the md5 checks.
- params = dict(parameters)
+ params = get_params()
super(FakeYDL, self).__init__(params)
self.result = []
@@ -62,3 +67,6 @@ def get_testcases():
for t in getattr(ie, '_TESTS', []):
t['name'] = type(ie).__name__[:-len('IE')]
yield t
+
+
+md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
diff --git a/test/test_age_restriction.py b/test/test_age_restriction.py
index 943f9a315..d500c6edc 100644
--- a/test/test_age_restriction.py
+++ b/test/test_age_restriction.py
@@ -1,14 +1,16 @@
#!/usr/bin/env python
-import sys
-import unittest
-
# Allow direct execution
import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import global_setup, try_rm
+global_setup()
+
from youtube_dl import YoutubeDL
-from helper import try_rm
def _download_restricted(url, filename, age):
diff --git a/test/test_all_urls.py b/test/test_all_urls.py
index ff1c86efe..56e5f80e1 100644
--- a/test/test_all_urls.py
+++ b/test/test_all_urls.py
@@ -1,14 +1,20 @@
#!/usr/bin/env python
-import sys
-import unittest
-
# Allow direct execution
import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from test.helper import get_testcases
+
+from youtube_dl.extractor import (
+ gen_extractors,
+ JustinTVIE,
+ YoutubeIE,
+)
-from youtube_dl.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE, gen_extractors
-from helper import get_testcases
class TestAllURLsMatching(unittest.TestCase):
def setUp(self):
diff --git a/test/test_dailymotion_subtitles.py b/test/test_dailymotion_subtitles.py
index ed2ad311d..c596415c4 100644
--- a/test/test_dailymotion_subtitles.py
+++ b/test/test_dailymotion_subtitles.py
@@ -1,18 +1,16 @@
#!/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__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL, global_setup, md5
+global_setup()
+
from youtube_dl.extractor import DailymotionIE
-from youtube_dl.utils import *
-from helper import FakeYDL
-
-md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class TestDailymotionSubtitles(unittest.TestCase):
def setUp(self):
diff --git a/test/test_download.py b/test/test_download.py
index fdf59bb5c..b9a9be11d 100644
--- a/test/test_download.py
+++ b/test/test_download.py
@@ -1,26 +1,31 @@
#!/usr/bin/env python
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import get_params, get_testcases, global_setup, try_rm, md5
+global_setup()
+
+
import hashlib
import io
-import os
import json
-import unittest
-import sys
import socket
-import binascii
-
-# Allow direct execution
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import youtube_dl.YoutubeDL
-from youtube_dl.utils import *
-
-PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+from youtube_dl.utils import (
+ compat_str,
+ compat_urllib_error,
+ DownloadError,
+ ExtractorError,
+ UnavailableVideoError,
+)
RETRIES = 3
-md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
-
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
self.to_stderr = self.to_screen
@@ -37,18 +42,12 @@ def _file_md5(fn):
with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest()
-import helper # Set up remaining global configuration
-from helper import get_testcases, try_rm
defs = get_testcases()
-with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
- parameters = json.load(pf)
-
class TestDownload(unittest.TestCase):
maxDiff = None
def setUp(self):
- self.parameters = parameters
self.defs = defs
### Dynamically generate tests
@@ -68,8 +67,7 @@ def generator(test_case):
print_skipping(test_case['skip'])
return
- params = self.parameters.copy()
- params.update(test_case.get('params', {}))
+ params = get_params(test_case.get('params', {}))
ydl = YoutubeDL(params)
ydl.add_default_info_extractors()
diff --git a/test/test_playlists.py b/test/test_playlists.py
index c33511333..d6a8d56df 100644
--- a/test/test_playlists.py
+++ b/test/test_playlists.py
@@ -1,13 +1,16 @@
#!/usr/bin/env python
# encoding: utf-8
-import sys
-import unittest
-import json
# Allow direct execution
import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL, global_setup
+global_setup()
+
from youtube_dl.extractor import (
DailymotionPlaylistIE,
@@ -16,10 +19,9 @@ from youtube_dl.extractor import (
UstreamChannelIE,
SoundcloudUserIE,
LivestreamIE,
+ NHLVideocenterIE,
)
-from youtube_dl.utils import *
-from helper import FakeYDL
class TestPlaylists(unittest.TestCase):
def assertIsPlaylist(self, info):
@@ -74,5 +76,14 @@ class TestPlaylists(unittest.TestCase):
self.assertEqual(result['title'], u'TEDCity2.0 (English)')
self.assertTrue(len(result['entries']) >= 4)
+ def test_nhl_videocenter(self):
+ dl = FakeYDL()
+ ie = NHLVideocenterIE(dl)
+ result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'999')
+ self.assertEqual(result['title'], u'Highlights')
+ self.assertEqual(len(result['entries']), 12)
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_utils.py b/test/test_utils.py
index ff2e9885b..f3fbff042 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1,14 +1,15 @@
#!/usr/bin/env python
-
-# Various small unit tests
-
-import sys
-import unittest
-import xml.etree.ElementTree
+# coding: utf-8
# Allow direct execution
import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+# Various small unit tests
+import xml.etree.ElementTree
#from youtube_dl.utils import htmlentity_transform
from youtube_dl.utils import (
@@ -20,6 +21,9 @@ from youtube_dl.utils import (
unified_strdate,
find_xpath_attr,
get_meta_content,
+ xpath_with_ns,
+ smuggle_url,
+ unsmuggle_url,
)
if sys.version_info < (3, 0):
@@ -141,5 +145,31 @@ class TestUtil(unittest.TestCase):
self.assertEqual(get_meta('description'), u'foo & bar')
self.assertEqual(get_meta('author'), 'Plato')
+ def test_xpath_with_ns(self):
+ testxml = u'''
+
+ The Author
+ http://server.com/download.mp3
+
+ '''
+ doc = xml.etree.ElementTree.fromstring(testxml)
+ find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
+ self.assertTrue(find('media:song') is not None)
+ self.assertEqual(find('media:song/media:author').text, u'The Author')
+ self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
+
+ def test_smuggle_url(self):
+ data = {u"ö": u"ö", u"abc": [3]}
+ url = 'https://foo.bar/baz?x=y#a'
+ smug_url = smuggle_url(url, data)
+ unsmug_url, unsmug_data = unsmuggle_url(smug_url)
+ self.assertEqual(url, unsmug_url)
+ self.assertEqual(data, unsmug_data)
+
+ res_url, res_data = unsmuggle_url(url)
+ self.assertEqual(res_url, url)
+ self.assertEqual(res_data, None)
+
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_write_annotations.py b/test/test_write_annotations.py
new file mode 100644
index 000000000..35defb895
--- /dev/null
+++ b/test/test_write_annotations.py
@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import get_params, global_setup, try_rm
+global_setup()
+
+
+import io
+
+import xml.etree.ElementTree
+
+import youtube_dl.YoutubeDL
+import youtube_dl.extractor
+
+
+class YoutubeDL(youtube_dl.YoutubeDL):
+ def __init__(self, *args, **kwargs):
+ super(YoutubeDL, self).__init__(*args, **kwargs)
+ self.to_stderr = self.to_screen
+
+params = get_params({
+ 'writeannotations': True,
+ 'skip_download': True,
+ 'writeinfojson': False,
+ 'format': 'flv',
+})
+
+
+
+TEST_ID = 'gr51aVj-mLg'
+ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
+EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
+
+class TestAnnotations(unittest.TestCase):
+ def setUp(self):
+ # Clear old files
+ self.tearDown()
+
+
+ def test_info_json(self):
+ expected = list(EXPECTED_ANNOTATIONS) #Two annotations could have the same text.
+ ie = youtube_dl.extractor.YoutubeIE()
+ ydl = YoutubeDL(params)
+ ydl.add_info_extractor(ie)
+ ydl.download([TEST_ID])
+ self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
+ annoxml = None
+ with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
+ annoxml = xml.etree.ElementTree.parse(annof)
+ self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
+ root = annoxml.getroot()
+ self.assertEqual(root.tag, 'document')
+ annotationsTag = root.find('annotations')
+ self.assertEqual(annotationsTag.tag, 'annotations')
+ annotations = annotationsTag.findall('annotation')
+
+ #Not all the annotations have TEXT children and the annotations are returned unsorted.
+ for a in annotations:
+ self.assertEqual(a.tag, 'annotation')
+ if a.get('type') == 'text':
+ textTag = a.find('TEXT')
+ text = textTag.text
+ self.assertTrue(text in expected) #assertIn only added in python 2.7
+ #remove the first occurance, there could be more than one annotation with the same text
+ expected.remove(text)
+ #We should have seen (and removed) all the expected annotation texts.
+ self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
+
+
+ def tearDown(self):
+ try_rm(ANNOTATIONS_FILE)
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_write_info_json.py b/test/test_write_info_json.py
index de6d5180f..a5b6f6972 100644
--- a/test/test_write_info_json.py
+++ b/test/test_write_info_json.py
@@ -1,37 +1,34 @@
#!/usr/bin/env python
# coding: utf-8
-import json
+# Allow direct execution
import os
import sys
import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-# Allow direct execution
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from test.helper import get_params, global_setup
+global_setup()
+
+
+import io
+import json
import youtube_dl.YoutubeDL
import youtube_dl.extractor
-from youtube_dl.utils import *
-PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
-
-# General configuration (from __init__, not very elegant...)
-jar = compat_cookiejar.CookieJar()
-cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
-proxy_handler = compat_urllib_request.ProxyHandler()
-opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
-compat_urllib_request.install_opener(opener)
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen
-with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
- params = json.load(pf)
-params['writeinfojson'] = True
-params['skip_download'] = True
-params['writedescription'] = True
+params = get_params({
+ 'writeinfojson': True,
+ 'skip_download': True,
+ 'writedescription': True,
+})
+
TEST_ID = 'BaW_jenozKc'
INFO_JSON_FILE = TEST_ID + '.mp4.info.json'
@@ -42,6 +39,7 @@ This is a test video for youtube-dl.
For more information, contact phihag@phihag.de .'''
+
class TestInfoJSON(unittest.TestCase):
def setUp(self):
# Clear old files
diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py
index 53e65816d..4b7a7847b 100644
--- a/test/test_youtube_lists.py
+++ b/test/test_youtube_lists.py
@@ -1,20 +1,26 @@
#!/usr/bin/env python
-import sys
-import unittest
-import json
-
# Allow direct execution
import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE, YoutubeShowIE
-from youtube_dl.utils import *
+from test.helper import FakeYDL, global_setup
+global_setup()
+
+
+from youtube_dl.extractor import (
+ YoutubeUserIE,
+ YoutubePlaylistIE,
+ YoutubeIE,
+ YoutubeChannelIE,
+ YoutubeShowIE,
+)
-from helper import FakeYDL
class TestYoutubeLists(unittest.TestCase):
- def assertIsPlaylist(self,info):
+ def assertIsPlaylist(self, info):
"""Make sure the info has '_type' set to 'playlist'"""
self.assertEqual(info['_type'], 'playlist')
@@ -100,7 +106,7 @@ class TestYoutubeLists(unittest.TestCase):
dl = FakeYDL()
ie = YoutubeShowIE(dl)
result = ie.extract('http://www.youtube.com/show/airdisasters')
- self.assertTrue(len(result) >= 4)
+ self.assertTrue(len(result) >= 3)
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py
index 5007d9a16..5e1ff5eb0 100644
--- a/test/test_youtube_signature.py
+++ b/test/test_youtube_signature.py
@@ -1,14 +1,18 @@
#!/usr/bin/env python
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import global_setup
+global_setup()
+
+
import io
import re
import string
-import sys
-import unittest
-
-# Allow direct execution
-import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import YoutubeIE
from youtube_dl.utils import compat_str, compat_urlretrieve
diff --git a/test/test_youtube_subtitles.py b/test/test_youtube_subtitles.py
index f9b0c1ad0..00430a338 100644
--- a/test/test_youtube_subtitles.py
+++ b/test/test_youtube_subtitles.py
@@ -1,69 +1,79 @@
#!/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__))))
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL, global_setup, md5
+global_setup()
+
from youtube_dl.extractor import YoutubeIE
-from youtube_dl.utils import *
-from helper import FakeYDL
-md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class TestYoutubeSubtitles(unittest.TestCase):
def setUp(self):
self.DL = FakeYDL()
self.url = 'QRS8MkLhQmM'
+
def getInfoDict(self):
IE = YoutubeIE(self.DL)
info_dict = IE.extract(self.url)
return info_dict
+
def getSubtitles(self):
info_dict = self.getInfoDict()
- return info_dict[0]['subtitles']
+ return info_dict[0]['subtitles']
+
def test_youtube_no_writesubtitles(self):
self.DL.params['writesubtitles'] = False
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
+
def test_youtube_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
+
def test_youtube_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
+
def test_youtube_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13)
+
def test_youtube_subtitles_sbv_format(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'sbv'
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
+
def test_youtube_subtitles_vtt_format(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'vtt'
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
+
def test_youtube_list_subtitles(self):
self.DL.expect_warning(u'Video doesn\'t have automatic captions')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
+
def test_youtube_automatic_captions(self):
self.url = '8YoUxe5ncPo'
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
+
def test_youtube_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'sAjKT8FhjI8'
@@ -71,6 +81,7 @@ class TestYoutubeSubtitles(unittest.TestCase):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
+
def test_youtube_multiple_langs(self):
self.url = 'QRS8MkLhQmM'
self.DL.params['writesubtitles'] = True
diff --git a/tox.ini b/tox.ini
index 53b461fdb..ed01e3386 100644
--- a/tox.ini
+++ b/tox.ini
@@ -1,5 +1,8 @@
[tox]
envlist = py26,py27,py33
[testenv]
-deps = nose
-commands = nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose test
+deps =
+ nose
+ coverage
+commands = nosetests --verbose {posargs:test} # --with-coverage --cover-package=youtube_dl --cover-html
+ # test.test_download:TestDownload.test_NowVideo
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py
index a79de3cd6..e01039419 100644
--- a/youtube_dl/FileDownloader.py
+++ b/youtube_dl/FileDownloader.py
@@ -270,6 +270,7 @@ class FileDownloader(object):
def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
+ test = self.params.get('test', False)
# Check for rtmpdump first
try:
@@ -291,6 +292,8 @@ class FileDownloader(object):
basic_args += ['--playpath', play_path]
if tc_url is not None:
basic_args += ['--tcUrl', url]
+ if test:
+ basic_args += ['--stop', '1']
args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
if self.params.get('verbose', False):
try:
@@ -300,7 +303,7 @@ class FileDownloader(object):
shell_quote = repr
self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args))
retval = subprocess.call(args)
- while retval == 2 or retval == 1:
+ while (retval == 2 or retval == 1) and not test:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
@@ -313,7 +316,7 @@ class FileDownloader(object):
self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = 0
break
- if retval == 0:
+ if retval == 0 or (test and retval == 2):
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[rtmpdump] %s bytes' % fsize)
self.try_rename(tmpfilename, filename)
diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py
index 3ee1d3c58..13b56ede5 100644
--- a/youtube_dl/PostProcessor.py
+++ b/youtube_dl/PostProcessor.py
@@ -3,7 +3,14 @@ import subprocess
import sys
import time
-from .utils import *
+
+from .utils import (
+ compat_subprocess_get_DEVNULL,
+ encodeFilename,
+ PostProcessingError,
+ shell_quote,
+ subtitles_filename,
+)
class PostProcessor(object):
@@ -82,6 +89,8 @@ class FFmpegPostProcessor(PostProcessor):
+ opts +
[encodeFilename(self._ffmpeg_filename_argument(out_path))])
+ if self._downloader.params.get('verbose', False):
+ self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout,stderr = p.communicate()
if p.returncode != 0:
@@ -177,7 +186,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
extension = self._preferredcodec
more_opts = []
if self._preferredquality is not None:
- if int(self._preferredquality) < 10:
+ # The opus codec doesn't support the -aq option
+ if int(self._preferredquality) < 10 and extension != 'opus':
more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
else:
more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
@@ -467,3 +477,35 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return True, information
+
+
+class FFmpegMetadataPP(FFmpegPostProcessor):
+ def run(self, info):
+ metadata = {}
+ if info.get('title') is not None:
+ metadata['title'] = info['title']
+ if info.get('upload_date') is not None:
+ metadata['date'] = info['upload_date']
+ if info.get('uploader') is not None:
+ metadata['artist'] = info['uploader']
+ elif info.get('uploader_id') is not None:
+ metadata['artist'] = info['uploader_id']
+
+ if not metadata:
+ self._downloader.to_screen(u'[ffmpeg] There isn\'t any metadata to add')
+ return True, info
+
+ filename = info['filepath']
+ ext = os.path.splitext(filename)[1][1:]
+ temp_filename = filename + u'.temp'
+
+ options = ['-c', 'copy']
+ for (name, value) in metadata.items():
+ options.extend(['-metadata', '%s="%s"' % (name, value)])
+ options.extend(['-f', ext])
+
+ self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
+ self.run_ffmpeg(filename, temp_filename, options)
+ os.remove(encodeFilename(filename))
+ os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+ return True, info
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index 073a3837c..c8054544a 100644
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -71,6 +71,7 @@ class YoutubeDL(object):
logtostderr: Log messages to stderr instead of stdout.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
+ writeannotations: Write the video annotations to a .annotations.xml file
writethumbnail: Write the thumbnail image to a file
writesubtitles: Write the video subtitles to a file
writeautomaticsub: Write the automatic subtitles to a file
@@ -119,7 +120,7 @@ class YoutubeDL(object):
and not params['restrictfilenames']):
# On Python 3, the Unicode filesystem API will throw errors (#1474)
self.report_warning(
- u'Assuming --restrict-filenames isnce file system encoding '
+ u'Assuming --restrict-filenames since file system encoding '
u'cannot encode all charactes. '
u'Set the LC_ALL environment variable to fix this.')
params['restrictfilenames'] = True
@@ -258,6 +259,10 @@ class YoutubeDL(object):
""" Report that the metadata file has been written """
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
+ def report_writeannotations(self, annofn):
+ """ Report that the annotations file has been written. """
+ self.to_screen(u'[info] Writing video annotations to: ' + annofn)
+
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
@@ -522,6 +527,18 @@ class YoutubeDL(object):
self.report_error(u'Cannot write description file ' + descfn)
return
+ if self.params.get('writeannotations', False):
+ try:
+ annofn = filename + u'.annotations.xml'
+ self.report_writeannotations(annofn)
+ with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
+ annofile.write(info_dict['annotations'])
+ except (KeyError, TypeError):
+ self.report_warning(u'There are no annotations to write.')
+ except (OSError, IOError):
+ self.report_error(u'Cannot write annotations file: ' + annofn)
+ return
+
subtitles_are_requested = any([self.params.get('writesubtitles', False),
self.params.get('writeautomaticsub')])
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 5cd708886..39785c918 100644
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -31,6 +31,7 @@ __authors__ = (
'Huarong Huo',
'Ismael Mejía',
'Steffan \'Ruirize\' James',
+ 'Andras Elso',
)
__license__ = 'Public Domain'
@@ -46,17 +47,43 @@ import shlex
import socket
import subprocess
import sys
-import warnings
+import traceback
import platform
-from .utils import *
+from .utils import (
+ compat_cookiejar,
+ compat_print,
+ compat_str,
+ compat_urllib_request,
+ DateRange,
+ decodeOption,
+ determine_ext,
+ DownloadError,
+ get_cachedir,
+ make_HTTPS_handler,
+ MaxDownloadsReached,
+ platform_name,
+ preferredencoding,
+ SameFileError,
+ std_headers,
+ write_string,
+ YoutubeDLHandler,
+)
from .update import update_self
from .version import __version__
-from .FileDownloader import *
+from .FileDownloader import (
+ FileDownloader,
+)
from .extractor import gen_extractors
from .YoutubeDL import YoutubeDL
-from .PostProcessor import *
+from .PostProcessor import (
+ FFmpegMetadataPP,
+ FFmpegVideoConvertor,
+ FFmpegExtractAudioPP,
+ FFmpegEmbedSubtitlePP,
+)
+
def parseOpts(overrideArguments=None):
def _readOptions(filename_bytes):
@@ -240,11 +267,11 @@ def parseOpts(overrideArguments=None):
help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
downloader.add_option('-r', '--rate-limit',
- dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
+ dest='ratelimit', metavar='LIMIT', help='maximum download rate in bytes per second (e.g. 50K or 4.2M)')
downloader.add_option('-R', '--retries',
dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
downloader.add_option('--buffer-size',
- dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is %default)', default="1024")
+ dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16K) (default is %default)', default="1024")
downloader.add_option('--no-resize-buffer',
action='store_true', dest='noresizebuffer',
help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
@@ -339,6 +366,9 @@ def parseOpts(overrideArguments=None):
filesystem.add_option('--write-info-json',
action='store_true', dest='writeinfojson',
help='write video metadata to a .info.json file', default=False)
+ filesystem.add_option('--write-annotations',
+ action='store_true', dest='writeannotations',
+ help='write video annotations to a .annotation file', default=False)
filesystem.add_option('--write-thumbnail',
action='store_true', dest='writethumbnail',
help='write thumbnail image to disk', default=False)
@@ -358,6 +388,8 @@ def parseOpts(overrideArguments=None):
help='do not overwrite post-processed files; the post-processed files are overwritten by default')
postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
help='embed subtitles in the video (only for mp4 videos)')
+ postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
+ help='add metadata to the files')
parser.add_option_group(general)
@@ -603,6 +635,7 @@ def _real_main(argv=None):
'nopart': opts.nopart,
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
+ 'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
'writesubtitles': opts.writesubtitles,
@@ -655,6 +688,9 @@ def _real_main(argv=None):
ydl.add_default_info_extractors()
# PostProcessors
+ # Add the metadata pp first, the other pps will copy it
+ if opts.addmetadata:
+ ydl.add_post_processor(FFmpegMetadataPP())
if opts.extractaudio:
ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
if opts.recodevideo:
@@ -683,7 +719,7 @@ def _real_main(argv=None):
if opts.cookiefile is not None:
try:
jar.save()
- except (IOError, OSError) as err:
+ except (IOError, OSError):
sys.exit(u'ERROR: unable to save cookie jar')
sys.exit(retcode)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index c01de6b5e..db69af361 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -2,7 +2,12 @@ from .appletrailers import AppleTrailersIE
from .addanime import AddAnimeIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE
-from .arte import ArteTvIE
+from .arte import (
+ ArteTvIE,
+ ArteTVPlus7IE,
+ ArteTVCreativeIE,
+ ArteTVFutureIE,
+)
from .auengine import AUEngineIE
from .bandcamp import BandcampIE
from .bliptv import BlipTVIE, BlipTVUserIE
@@ -12,6 +17,7 @@ from .brightcove import BrightcoveIE
from .c56 import C56IE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
+from .cinemassacre import CinemassacreIE
from .cnn import CNNIE
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE
@@ -34,6 +40,7 @@ from .eighttracks import EightTracksIE
from .escapist import EscapistIE
from .exfm import ExfmIE
from .facebook import FacebookIE
+from .faz import FazIE
from .fktv import (
FKTVIE,
FKTVPosteckeIE,
@@ -60,6 +67,7 @@ from .ign import IGNIE, OneUPIE
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
+from .internetvideoarchive import InternetVideoArchiveIE
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
@@ -80,6 +88,8 @@ from .naver import NaverIE
from .nba import NBAIE
from .nbc import NBCNewsIE
from .newgrounds import NewgroundsIE
+from .nhl import NHLIE, NHLVideocenterIE
+from .nowvideo import NowVideoIE
from .ooyala import OoyalaIE
from .orf import ORFIE
from .pbs import PBSIE
@@ -89,8 +99,10 @@ from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .ringtv import RingTVIE
from .ro220 import Ro220IE
+from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
+from .rutube import RutubeIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .slideshare import SlideshareIE
@@ -101,7 +113,9 @@ from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE
from .steam import SteamIE
+from .sztvhu import SztvHuIE
from .teamcoco import TeamcocoIE
+from .techtalks import TechTalksIE
from .ted import TEDIE
from .tf1 import TF1IE
from .thisav import ThisAVIE
@@ -118,10 +132,13 @@ from .veoh import VeohIE
from .vevo import VevoIE
from .vice import ViceIE
from .viddler import ViddlerIE
+from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE
+from .videopremium import VideoPremiumIE
from .vimeo import VimeoIE, VimeoChannelIE
from .vine import VineIE
from .wat import WatIE
+from .websurg import WeBSurgIE
from .weibo import WeiboIE
from .wimp import WimpIE
from .worldstarhiphop import WorldStarHipHopIE
diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py
index 69b3b0ad7..5ee8a67b1 100644
--- a/youtube_dl/extractor/arte.py
+++ b/youtube_dl/extractor/arte.py
@@ -1,3 +1,4 @@
+# encoding: utf-8
import re
import json
import xml.etree.ElementTree
@@ -7,15 +8,15 @@ from ..utils import (
ExtractorError,
find_xpath_attr,
unified_strdate,
+ determine_ext,
+ get_element_by_id,
)
+# There are different sources of video in arte.tv, the extraction process
+# is different for each one. The videos usually expire in 7 days, so we can't
+# add tests.
+
class ArteTvIE(InfoExtractor):
- """
- There are two sources of video in arte.tv: videos.arte.tv and
- www.arte.tv/guide, the extraction process is different for each one.
- The videos expire in 7 days, so we can't add tests.
- """
- _EMISSION_URL = r'(?:http://)?www\.arte.tv/guide/(?Pfr|de)/(?:(?:sendungen|emissions)/)?(?P.*?)/(?P.*?)(\?.*)?'
_VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?Pfr|de)/.*-(?P.*?).html'
_LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?Pfr|de)/(?P.+?)/(?P.+)'
_LIVE_URL = r'index-[0-9]+\.html$'
@@ -24,7 +25,7 @@ class ArteTvIE(InfoExtractor):
@classmethod
def suitable(cls, url):
- return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL, cls._LIVEWEB_URL))
+ return any(re.match(regex, url) for regex in (cls._VIDEOS_URL, cls._LIVEWEB_URL))
# TODO implement Live Stream
# from ..utils import compat_urllib_parse
@@ -55,14 +56,6 @@ class ArteTvIE(InfoExtractor):
# video_url = u'%s/%s' % (info.get('url'), info.get('path'))
def _real_extract(self, url):
- mobj = re.match(self._EMISSION_URL, url)
- if mobj is not None:
- lang = mobj.group('lang')
- # This is not a real id, it can be for example AJT for the news
- # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
- video_id = mobj.group('id')
- return self._extract_emission(url, video_id, lang)
-
mobj = re.match(self._VIDEOS_URL, url)
if mobj is not None:
id = mobj.group('id')
@@ -80,49 +73,6 @@ class ArteTvIE(InfoExtractor):
# self.extractLiveStream(url)
# return
- def _extract_emission(self, url, video_id, lang):
- """Extract from www.arte.tv/guide"""
- webpage = self._download_webpage(url, video_id)
- json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
-
- json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
- self.report_extraction(video_id)
- info = json.loads(json_info)
- player_info = info['videoJsonPlayer']
-
- info_dict = {'id': player_info['VID'],
- 'title': player_info['VTI'],
- 'description': player_info.get('VDE'),
- 'upload_date': unified_strdate(player_info['VDA'].split(' ')[0]),
- 'thumbnail': player_info['programImage'],
- 'ext': 'flv',
- }
-
- formats = player_info['VSR'].values()
- def _match_lang(f):
- # Return true if that format is in the language of the url
- if lang == 'fr':
- l = 'F'
- elif lang == 'de':
- l = 'A'
- regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
- return any(re.match(r, f['versionCode']) for r in regexes)
- # Some formats may not be in the same language as the url
- formats = filter(_match_lang, formats)
- # We order the formats by quality
- formats = sorted(formats, key=lambda f: int(f['height']))
- # Prefer videos without subtitles in the same language
- formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f['versionCode']) is None)
- # Pick the best quality
- format_info = formats[-1]
- if format_info['mediaType'] == u'rtmp':
- info_dict['url'] = format_info['streamer']
- info_dict['play_path'] = 'mp4:' + format_info['url']
- else:
- info_dict['url'] = format_info['url']
-
- return info_dict
-
def _extract_video(self, url, video_id, lang):
"""Extract from videos.arte.tv"""
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
@@ -172,3 +122,110 @@ class ArteTvIE(InfoExtractor):
'ext': 'flv',
'thumbnail': self._og_search_thumbnail(webpage),
}
+
+
+class ArteTVPlus7IE(InfoExtractor):
+ IE_NAME = u'arte.tv:+7'
+ _VALID_URL = r'https?://www\.arte.tv/guide/(?Pfr|de)/(?:(?:sendungen|emissions)/)?(?P.*?)/(?P.*?)(\?.*)?'
+
+ @classmethod
+ def _extract_url_info(cls, url):
+ mobj = re.match(cls._VALID_URL, url)
+ lang = mobj.group('lang')
+ # This is not a real id, it can be for example AJT for the news
+ # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
+ video_id = mobj.group('id')
+ return video_id, lang
+
+ def _real_extract(self, url):
+ video_id, lang = self._extract_url_info(url)
+ webpage = self._download_webpage(url, video_id)
+ return self._extract_from_webpage(webpage, video_id, lang)
+
+ def _extract_from_webpage(self, webpage, video_id, lang):
+ json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+
+ json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
+ self.report_extraction(video_id)
+ info = json.loads(json_info)
+ player_info = info['videoJsonPlayer']
+
+ info_dict = {
+ 'id': player_info['VID'],
+ 'title': player_info['VTI'],
+ 'description': player_info.get('VDE'),
+ 'upload_date': unified_strdate(player_info.get('VDA', '').split(' ')[0]),
+ 'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
+ }
+
+ formats = player_info['VSR'].values()
+ def _match_lang(f):
+ if f.get('versionCode') is None:
+ return True
+ # Return true if that format is in the language of the url
+ if lang == 'fr':
+ l = 'F'
+ elif lang == 'de':
+ l = 'A'
+ regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
+ return any(re.match(r, f['versionCode']) for r in regexes)
+ # Some formats may not be in the same language as the url
+ formats = filter(_match_lang, formats)
+ # Some formats use the m3u8 protocol
+ formats = filter(lambda f: f.get('videoFormat') != 'M3U8', formats)
+ # We order the formats by quality
+ formats = sorted(formats, key=lambda f: int(f.get('height',-1)))
+ # Prefer videos without subtitles in the same language
+ formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f.get('versionCode', '')) is None)
+ # Pick the best quality
+ def _format(format_info):
+ info = {
+ 'width': format_info.get('width'),
+ 'height': format_info.get('height'),
+ }
+ if format_info['mediaType'] == u'rtmp':
+ info['url'] = format_info['streamer']
+ info['play_path'] = 'mp4:' + format_info['url']
+ info['ext'] = 'flv'
+ else:
+ info['url'] = format_info['url']
+ info['ext'] = determine_ext(info['url'])
+ return info
+ info_dict['formats'] = [_format(f) for f in formats]
+ # TODO: Remove when #980 has been merged
+ info_dict.update(info_dict['formats'][-1])
+
+ return info_dict
+
+
+# It also uses the arte_vp_url url from the webpage to extract the information
+class ArteTVCreativeIE(ArteTVPlus7IE):
+ IE_NAME = u'arte.tv:creative'
+ _VALID_URL = r'https?://creative\.arte\.tv/(?Pfr|de)/magazine?/(?P.+)'
+
+ _TEST = {
+ u'url': u'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
+ u'file': u'050489-002.mp4',
+ u'info_dict': {
+ u'title': u'Agentur Amateur #2 - Corporate Design',
+ },
+ }
+
+
+class ArteTVFutureIE(ArteTVPlus7IE):
+ IE_NAME = u'arte.tv:future'
+ _VALID_URL = r'https?://future\.arte\.tv/(?Pfr|de)/(thema|sujet)/.*?#article-anchor-(?P\d+)'
+
+ _TEST = {
+ u'url': u'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
+ u'file': u'050940-003.mp4',
+ u'info_dict': {
+ u'title': u'Les champignons au secours de la planète',
+ },
+ }
+
+ def _real_extract(self, url):
+ anchor_id, lang = self._extract_url_info(url)
+ webpage = self._download_webpage(url, anchor_id)
+ row = get_element_by_id(anchor_id, webpage)
+ return self._extract_from_webpage(row, anchor_id, lang)
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index 745212f2f..1392f382a 100644
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -53,6 +53,8 @@ class BrightcoveIE(InfoExtractor):
# Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
object_str = re.sub(r'(',
lambda m: m.group(1) + '/>', object_str)
+ # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
+ object_str = object_str.replace(u'<--', u'