aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-12-13 12:24:42 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-12-13 12:35:45 +0100
commit1cc79574fc5df21bf35dccf61eac0e9e75ed8d20 (patch)
tree5cc2bd2a2faba0ac5e8371892e3ef09ab5338080
parent20e35880bf7413c5085c1ade96af0fc6e56d84d1 (diff)
Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
-rw-r--r--youtube_dl/downloader/common.py2
-rw-r--r--youtube_dl/downloader/f4m.py4
-rw-r--r--youtube_dl/downloader/hls.py4
-rw-r--r--youtube_dl/downloader/http.py5
-rw-r--r--youtube_dl/downloader/rtmp.py2
-rw-r--r--youtube_dl/extractor/allocine.py5
-rw-r--r--youtube_dl/extractor/aol.py1
-rw-r--r--youtube_dl/extractor/appletrailers.py2
-rw-r--r--youtube_dl/extractor/auengine.py2
-rw-r--r--youtube_dl/extractor/bambuser.py2
-rw-r--r--youtube_dl/extractor/bandcamp.py4
-rw-r--r--youtube_dl/extractor/bet.py2
-rw-r--r--youtube_dl/extractor/bilibili.py7
-rw-r--r--youtube_dl/extractor/brightcove.py19
-rw-r--r--youtube_dl/extractor/ceskatelevize.py4
-rw-r--r--youtube_dl/extractor/comedycentral.py4
-rw-r--r--youtube_dl/extractor/condenast.py6
-rw-r--r--youtube_dl/extractor/crunchyroll.py6
-rw-r--r--youtube_dl/extractor/dailymotion.py10
-rw-r--r--youtube_dl/extractor/daum.py2
-rw-r--r--youtube_dl/extractor/ehow.py11
-rw-r--r--youtube_dl/extractor/eighttracks.py2
-rw-r--r--youtube_dl/extractor/escapist.py5
-rw-r--r--youtube_dl/extractor/everyonesmixtape.py4
-rw-r--r--youtube_dl/extractor/extremetube.py8
-rw-r--r--youtube_dl/extractor/fc2.py13
-rw-r--r--youtube_dl/extractor/firedrive.py11
-rw-r--r--youtube_dl/extractor/fourtube.py14
-rw-r--r--youtube_dl/extractor/franceculture.py2
-rw-r--r--youtube_dl/extractor/francetv.py10
-rw-r--r--youtube_dl/extractor/gamespot.py4
-rw-r--r--youtube_dl/extractor/gdcvault.py2
-rw-r--r--youtube_dl/extractor/golem.py4
-rw-r--r--youtube_dl/extractor/googlesearch.py2
-rw-r--r--youtube_dl/extractor/gorillavid.py8
-rw-r--r--youtube_dl/extractor/hostingbulk.py8
-rw-r--r--youtube_dl/extractor/hypem.py11
-rw-r--r--youtube_dl/extractor/imdb.py2
-rw-r--r--youtube_dl/extractor/infoq.py7
-rw-r--r--youtube_dl/extractor/internetvideoarchive.py4
-rw-r--r--youtube_dl/extractor/iprima.py4
-rw-r--r--youtube_dl/extractor/ivi.py4
-rw-r--r--youtube_dl/extractor/keezmovies.py7
-rw-r--r--youtube_dl/extractor/livestream.py4
-rw-r--r--youtube_dl/extractor/lynda.py6
-rw-r--r--youtube_dl/extractor/malemotion.py38
-rw-r--r--youtube_dl/extractor/metacafe.py4
-rw-r--r--youtube_dl/extractor/mit.py4
-rw-r--r--youtube_dl/extractor/mitele.py13
-rw-r--r--youtube_dl/extractor/mixcloud.py4
-rw-r--r--youtube_dl/extractor/moevideo.py6
-rw-r--r--youtube_dl/extractor/mofosex.py6
-rw-r--r--youtube_dl/extractor/moniker.py7
-rw-r--r--youtube_dl/extractor/mooshare.py10
-rw-r--r--youtube_dl/extractor/motorsport.py10
-rw-r--r--youtube_dl/extractor/movieclips.py4
-rw-r--r--youtube_dl/extractor/mtv.py4
-rw-r--r--youtube_dl/extractor/myspass.py5
-rw-r--r--youtube_dl/extractor/naver.py8
-rw-r--r--youtube_dl/extractor/nbc.py4
-rw-r--r--youtube_dl/extractor/nfb.py14
-rw-r--r--youtube_dl/extractor/nfl.py4
-rw-r--r--youtube_dl/extractor/niconico.py10
-rw-r--r--youtube_dl/extractor/noco.py10
-rw-r--r--youtube_dl/extractor/nosvideo.py7
-rw-r--r--youtube_dl/extractor/novamov.py4
-rw-r--r--youtube_dl/extractor/nuvid.py9
-rw-r--r--youtube_dl/extractor/photobucket.py5
-rw-r--r--youtube_dl/extractor/played.py7
-rw-r--r--youtube_dl/extractor/playfm.py4
-rw-r--r--youtube_dl/extractor/playvid.py22
-rw-r--r--youtube_dl/extractor/pornhub.py8
-rw-r--r--youtube_dl/extractor/promptfile.py8
-rw-r--r--youtube_dl/extractor/prosiebensat1.py4
-rw-r--r--youtube_dl/extractor/quickvid.py4
-rw-r--r--youtube_dl/extractor/rai.py4
-rw-r--r--youtube_dl/extractor/rts.py4
-rw-r--r--youtube_dl/extractor/rutube.py13
-rw-r--r--youtube_dl/extractor/screencast.py11
-rw-r--r--youtube_dl/extractor/shared.py38
-rw-r--r--youtube_dl/extractor/sharesix.py4
-rw-r--r--youtube_dl/extractor/sina.py2
-rw-r--r--youtube_dl/extractor/slideshare.py4
-rw-r--r--youtube_dl/extractor/smotri.py4
-rw-r--r--youtube_dl/extractor/sockshare.py13
-rw-r--r--youtube_dl/extractor/soundcloud.py5
-rw-r--r--youtube_dl/extractor/spankwire.py8
-rw-r--r--youtube_dl/extractor/sportdeutschland.py4
-rw-r--r--youtube_dl/extractor/streamcloud.py2
-rw-r--r--youtube_dl/extractor/streamcz.py6
-rw-r--r--youtube_dl/extractor/tapely.py6
-rw-r--r--youtube_dl/extractor/ted.py2
-rw-r--r--youtube_dl/extractor/theplatform.py4
-rw-r--r--youtube_dl/extractor/tlc.py2
-rw-r--r--youtube_dl/extractor/tube8.py4
-rw-r--r--youtube_dl/extractor/tutv.py8
-rw-r--r--youtube_dl/extractor/twitch.py4
-rw-r--r--youtube_dl/extractor/udemy.py4
-rw-r--r--youtube_dl/extractor/urort.py6
-rw-r--r--youtube_dl/extractor/ustream.py2
-rw-r--r--youtube_dl/extractor/vbox7.py12
-rw-r--r--youtube_dl/extractor/veehd.py9
-rw-r--r--youtube_dl/extractor/veoh.py4
-rw-r--r--youtube_dl/extractor/vevo.py4
-rw-r--r--youtube_dl/extractor/videodetective.py9
-rw-r--r--youtube_dl/extractor/videomega.py10
-rw-r--r--youtube_dl/extractor/vk.py11
-rw-r--r--youtube_dl/extractor/vodlocker.py6
-rw-r--r--youtube_dl/extractor/vube.py4
-rw-r--r--youtube_dl/extractor/vuclip.py9
-rw-r--r--youtube_dl/extractor/wdr.py5
-rw-r--r--youtube_dl/extractor/wistia.py8
-rw-r--r--youtube_dl/extractor/xbef.py9
-rw-r--r--youtube_dl/extractor/xnxx.py9
-rw-r--r--youtube_dl/extractor/xtube.py8
-rw-r--r--youtube_dl/extractor/xvideos.py22
-rw-r--r--youtube_dl/extractor/yahoo.py6
-rw-r--r--youtube_dl/extractor/ynet.py2
-rw-r--r--youtube_dl/extractor/youporn.py5
-rw-r--r--youtube_dl/swfinterp.py2
120 files changed, 437 insertions, 378 deletions
diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py
index 2a566eabe..8181bca09 100644
--- a/youtube_dl/downloader/common.py
+++ b/youtube_dl/downloader/common.py
@@ -5,8 +5,8 @@ import re
import sys
import time
+from ..compat import compat_str
from ..utils import (
- compat_str,
encodeFilename,
format_bytes,
timeconvert,
diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py
index 7cd22c504..00f3a026c 100644
--- a/youtube_dl/downloader/f4m.py
+++ b/youtube_dl/downloader/f4m.py
@@ -9,10 +9,12 @@ import xml.etree.ElementTree as etree
from .common import FileDownloader
from .http import HttpFD
+from ..compat import (
+ compat_urlparse,
+)
from ..utils import (
struct_pack,
struct_unpack,
- compat_urlparse,
format_bytes,
encodeFilename,
sanitize_open,
diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py
index ad26cfa40..5bb0f3cfd 100644
--- a/youtube_dl/downloader/hls.py
+++ b/youtube_dl/downloader/hls.py
@@ -6,9 +6,11 @@ import subprocess
from ..postprocessor.ffmpeg import FFmpegPostProcessor
from .common import FileDownloader
-from ..utils import (
+from ..compat import (
compat_urlparse,
compat_urllib_request,
+)
+from ..utils import (
check_executable,
encodeFilename,
)
diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py
index 224962e86..e68f20c9f 100644
--- a/youtube_dl/downloader/http.py
+++ b/youtube_dl/downloader/http.py
@@ -4,11 +4,12 @@ import os
import time
from .common import FileDownloader
-from ..utils import (
+from ..compat import (
compat_urllib_request,
compat_urllib_error,
+)
+from ..utils import (
ContentTooShortError,
-
encodeFilename,
sanitize_open,
format_bytes,
diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py
index 58ae2005c..575912675 100644
--- a/youtube_dl/downloader/rtmp.py
+++ b/youtube_dl/downloader/rtmp.py
@@ -7,9 +7,9 @@ import sys
import time
from .common import FileDownloader
+from ..compat import compat_str
from ..utils import (
check_executable,
- compat_str,
encodeFilename,
format_bytes,
get_exe_version,
diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py
index 398e93bfb..623aeaf34 100644
--- a/youtube_dl/extractor/allocine.py
+++ b/youtube_dl/extractor/allocine.py
@@ -5,10 +5,9 @@ import re
import json
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- compat_str,
qualities,
- determine_ext,
)
@@ -75,9 +74,7 @@ class AllocineIE(InfoExtractor):
'format_id': format_id,
'quality': quality(format_id),
'url': v,
- 'ext': determine_ext(v),
})
-
self._sort_formats(formats)
return {
diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py
index 185ee3693..b51eafc45 100644
--- a/youtube_dl/extractor/aol.py
+++ b/youtube_dl/extractor/aol.py
@@ -68,4 +68,3 @@ class AolIE(InfoExtractor):
'title': title,
'entries': entries,
}
-
diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py
index 0c01fa1a1..7cd0482c7 100644
--- a/youtube_dl/extractor/appletrailers.py
+++ b/youtube_dl/extractor/appletrailers.py
@@ -4,8 +4,8 @@ import re
import json
from .common import InfoExtractor
+from ..compat import compat_urlparse
from ..utils import (
- compat_urlparse,
int_or_none,
)
diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py
index 1c765532a..014a21952 100644
--- a/youtube_dl/extractor/auengine.py
+++ b/youtube_dl/extractor/auengine.py
@@ -3,8 +3,8 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import compat_urllib_parse
from ..utils import (
- compat_urllib_parse,
determine_ext,
ExtractorError,
)
diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py
index 1ca0b7cf2..98e1443ab 100644
--- a/youtube_dl/extractor/bambuser.py
+++ b/youtube_dl/extractor/bambuser.py
@@ -5,7 +5,7 @@ import json
import itertools
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
)
diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index acddbc8f1..9fb770cb1 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -4,9 +4,11 @@ import json
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
compat_urlparse,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py
index c1fc433f7..003e50002 100644
--- a/youtube_dl/extractor/bet.py
+++ b/youtube_dl/extractor/bet.py
@@ -1,8 +1,8 @@
from __future__ import unicode_literals
from .common import InfoExtractor
+from ..compat import compat_urllib_parse
from ..utils import (
- compat_urllib_parse,
xpath_text,
xpath_with_ns,
int_or_none,
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 0d5889f5d..241b904a9 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -4,8 +4,8 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import compat_parse_qs
from ..utils import (
- compat_parse_qs,
ExtractorError,
int_or_none,
unified_strdate,
@@ -29,10 +29,9 @@ class BiliBiliIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+
video_code = self._search_regex(
r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index bf18a97e0..1eca00470 100644
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -6,20 +6,21 @@ import json
import xml.etree.ElementTree
from .common import InfoExtractor
-from ..utils import (
- compat_urllib_parse,
- find_xpath_attr,
- fix_xml_ampersands,
- compat_urlparse,
- compat_str,
- compat_urllib_request,
+from ..compat import (
compat_parse_qs,
+ compat_str,
+ compat_urllib_parse,
compat_urllib_parse_urlparse,
-
+ compat_urllib_request,
+ compat_urlparse,
+)
+from ..utils import (
determine_ext,
ExtractorError,
- unsmuggle_url,
+ find_xpath_attr,
+ fix_xml_ampersands,
unescapeHTML,
+ unsmuggle_url,
)
diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py
index 97feb6704..2f866f3ef 100644
--- a/youtube_dl/extractor/ceskatelevize.py
+++ b/youtube_dl/extractor/ceskatelevize.py
@@ -4,10 +4,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
compat_urllib_parse,
compat_urllib_parse_urlparse,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 2e3ef3fda..48e2410b6 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
compat_urllib_parse,
+)
+from ..utils import (
ExtractorError,
float_or_none,
unified_strdate,
diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py
index 7a7e79360..3db4db4e4 100644
--- a/youtube_dl/extractor/condenast.py
+++ b/youtube_dl/extractor/condenast.py
@@ -5,12 +5,14 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
- orderedSet,
compat_urllib_parse_urlparse,
compat_urlparse,
)
+from ..utils import (
+ orderedSet,
+)
class CondeNastIE(InfoExtractor):
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index d7e2b841e..8f1ea02e7 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -10,10 +10,12 @@ import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
+ ExtractorError,
bytes_to_intlist,
intlist_to_bytes,
unified_strdate,
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 936c13cd6..cf5841a7c 100644
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -8,13 +8,15 @@ import itertools
from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
- compat_urllib_request,
+from ..compat import (
compat_str,
+ compat_urllib_request,
+)
+from ..utils import (
+ ExtractorError,
+ int_or_none,
orderedSet,
str_to_int,
- int_or_none,
- ExtractorError,
unescapeHTML,
)
diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index 45d66e2e6..c6b813f58 100644
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -5,7 +5,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py
index b766e17f2..9cb1bf301 100644
--- a/youtube_dl/extractor/ehow.py
+++ b/youtube_dl/extractor/ehow.py
@@ -1,8 +1,6 @@
from __future__ import unicode_literals
-import re
-
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
from .common import InfoExtractor
@@ -24,11 +22,10 @@ class EHowIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
- webpage, 'video URL')
+ video_url = self._search_regex(
+ r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
final_url = compat_urllib_parse.unquote(video_url)
uploader = self._html_search_meta('uploader', webpage)
title = self._og_search_title(webpage).replace(' | eHow', '')
diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py
index f4c1e2a72..a30a1f330 100644
--- a/youtube_dl/extractor/eighttracks.py
+++ b/youtube_dl/extractor/eighttracks.py
@@ -6,7 +6,7 @@ import random
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
)
diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py
index 476fc22b9..e240cb859 100644
--- a/youtube_dl/extractor/escapist.py
+++ b/youtube_dl/extractor/escapist.py
@@ -3,9 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
-
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py
index d237a8281..d872d828f 100644
--- a/youtube_dl/extractor/everyonesmixtape.py
+++ b/youtube_dl/extractor/everyonesmixtape.py
@@ -3,8 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index aacbf1414..36ba33128 100644
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -3,16 +3,18 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
+)
+from ..utils import (
str_to_int,
)
class ExtremeTubeIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
_TESTS = [{
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
@@ -31,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
+ video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py
index 6f5d23559..81ceace53 100644
--- a/youtube_dl/extractor/fc2.py
+++ b/youtube_dl/extractor/fc2.py
@@ -1,19 +1,20 @@
#! -*- coding: utf-8 -*-
from __future__ import unicode_literals
-import re
import hashlib
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_request,
compat_urlparse,
)
+from ..utils import (
+ ExtractorError,
+)
class FC2IE(InfoExtractor):
- _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)'
+ _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
IE_NAME = 'fc2'
_TEST = {
'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
@@ -26,9 +27,7 @@ class FC2IE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
self._downloader.cookiejar.clear_session_cookies() # must clear
diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py
index af439ccfe..3191116d9 100644
--- a/youtube_dl/extractor/firedrive.py
+++ b/youtube_dl/extractor/firedrive.py
@@ -4,11 +4,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
+from ..utils import (
+ ExtractorError,
+)
class FiredriveIE(InfoExtractor):
@@ -28,11 +30,8 @@ class FiredriveIE(InfoExtractor):
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
url = 'http://firedrive.com/file/%s' % video_id
-
webpage = self._download_webpage(url, video_id)
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py
index b22ce2acb..7187e0752 100644
--- a/youtube_dl/extractor/fourtube.py
+++ b/youtube_dl/extractor/fourtube.py
@@ -3,12 +3,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
- unified_strdate,
- str_to_int,
- parse_duration,
+)
+from ..utils import (
clean_html,
+ parse_duration,
+ str_to_int,
+ unified_strdate,
)
@@ -31,9 +33,7 @@ class FourTubeIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage_url = 'http://www.4tube.com/videos/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py
index 898e0dda7..0c2972162 100644
--- a/youtube_dl/extractor/franceculture.py
+++ b/youtube_dl/extractor/franceculture.py
@@ -5,7 +5,7 @@ import json
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_parse_qs,
compat_urlparse,
)
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index e0420a48f..bbc760a49 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -6,13 +6,15 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+ compat_urllib_parse_urlparse,
compat_urlparse,
- ExtractorError,
+)
+from ..utils import (
clean_html,
- parse_duration,
- compat_urllib_parse_urlparse,
+ ExtractorError,
int_or_none,
+ parse_duration,
)
diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py
index d570e3f6a..47373e215 100644
--- a/youtube_dl/extractor/gamespot.py
+++ b/youtube_dl/extractor/gamespot.py
@@ -4,9 +4,11 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urlparse,
+)
+from ..utils import (
unescapeHTML,
)
diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py
index de14ae1fb..d453ec010 100644
--- a/youtube_dl/extractor/gdcvault.py
+++ b/youtube_dl/extractor/gdcvault.py
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
diff --git a/youtube_dl/extractor/golem.py b/youtube_dl/extractor/golem.py
index 53714f47f..2bfb99040 100644
--- a/youtube_dl/extractor/golem.py
+++ b/youtube_dl/extractor/golem.py
@@ -2,8 +2,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
+)
+from ..utils import (
determine_ext,
)
diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py
index 469e1f935..498304cb2 100644
--- a/youtube_dl/extractor/googlesearch.py
+++ b/youtube_dl/extractor/googlesearch.py
@@ -4,7 +4,7 @@ import itertools
import re
from .common import SearchInfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
index 1ac1da856..ae24aff84 100644
--- a/youtube_dl/extractor/gorillavid.py
+++ b/youtube_dl/extractor/gorillavid.py
@@ -4,11 +4,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
- determine_ext,
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
+ ExtractorError,
int_or_none,
)
@@ -106,7 +107,6 @@ class GorillaVidIE(InfoExtractor):
formats = [{
'format_id': 'sd',
'url': video_url,
- 'ext': determine_ext(video_url),
'quality': 1,
}]
diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py
index 8e812b669..704d0285d 100644
--- a/youtube_dl/extractor/hostingbulk.py
+++ b/youtube_dl/extractor/hostingbulk.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+)
from ..utils import (
ExtractorError,
- compat_urllib_request,
int_or_none,
urlencode_postdata,
)
@@ -30,9 +32,7 @@ class HostingBulkIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
# Custom request with cookie to set language to English, so our file
diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py
index 6d0d847c6..aa0724a02 100644
--- a/youtube_dl/extractor/hypem.py
+++ b/youtube_dl/extractor/hypem.py
@@ -1,20 +1,20 @@
from __future__ import unicode_literals
import json
-import re
import time
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
-
+)
+from ..utils import (
ExtractorError,
)
class HypemIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+ _VALID_URL = r'http://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
_TEST = {
'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
@@ -27,8 +27,7 @@ class HypemIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- track_id = mobj.group(1)
+ track_id = self._match_id(url)
data = {'ax': 1, 'ts': time.time()}
data_encoded = compat_urllib_parse.urlencode(data)
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index f2c1c10f5..13a53a0cb 100644
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -4,7 +4,7 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
)
diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py
index e76dd222d..f25f43664 100644
--- a/youtube_dl/extractor/infoq.py
+++ b/youtube_dl/extractor/infoq.py
@@ -1,10 +1,9 @@
from __future__ import unicode_literals
import base64
-import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
@@ -24,9 +23,7 @@ class InfoQIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py
index 1e4799187..c813d4b82 100644
--- a/youtube_dl/extractor/internetvideoarchive.py
+++ b/youtube_dl/extractor/internetvideoarchive.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
compat_urllib_parse,
+)
+from ..utils import (
xpath_with_ns,
)
diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py
index 4247d6391..8529bedfc 100644
--- a/youtube_dl/extractor/iprima.py
+++ b/youtube_dl/extractor/iprima.py
@@ -6,8 +6,10 @@ from random import random
from math import floor
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py
index f0fba1adb..7a400323d 100644
--- a/youtube_dl/extractor/ivi.py
+++ b/youtube_dl/extractor/ivi.py
@@ -5,8 +5,10 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py
index 75b63cffb..97dcb518a 100644
--- a/youtube_dl/extractor/keezmovies.py
+++ b/youtube_dl/extractor/keezmovies.py
@@ -4,7 +4,7 @@ import os
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
@@ -15,7 +15,7 @@ from ..aes import (
class KeezMoviesIE(InfoExtractor):
- _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)'
+ _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
_TEST = {
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
'file': '1214711.mp4',
@@ -27,8 +27,7 @@ class KeezMoviesIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
+ video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py
index 03c4691c6..5247c6f58 100644
--- a/youtube_dl/extractor/livestream.py
+++ b/youtube_dl/extractor/livestream.py
@@ -4,10 +4,12 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
compat_urllib_parse_urlparse,
compat_urlparse,
+)
+from ..utils import (
ExtractorError,
find_xpath_attr,
int_or_none,
diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
index 2160d6cb0..26e84970d 100644
--- a/youtube_dl/extractor/lynda.py
+++ b/youtube_dl/extractor/lynda.py
@@ -5,12 +5,14 @@ import json
from .subtitles import SubtitlesInfoExtractor
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+ compat_str,
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
int_or_none,
- compat_str,
)
diff --git a/youtube_dl/extractor/malemotion.py b/youtube_dl/extractor/malemotion.py
index 1abf6e4f8..0b85a59d1 100644
--- a/youtube_dl/extractor/malemotion.py
+++ b/youtube_dl/extractor/malemotion.py
@@ -1,43 +1,33 @@
+# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
class MalemotionIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
+ _VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
_TEST = {
- 'url': 'http://malemotion.com/video/bien-dur.10ew',
- 'file': '10ew.mp4',
- 'md5': 'b3cc49f953b107e4a363cdff07d100ce',
+ 'url': 'http://malemotion.com/video/bete-de-concours.ltc',
+ 'md5': '3013e53a0afbde2878bc39998c33e8a5',
'info_dict': {
- "title": "Bien dur",
- "age_limit": 18,
+ 'id': 'ltc',
+ 'ext': 'mp4',
+ 'title': 'Bête de Concours',
+ 'age_limit': 18,
},
- 'skip': 'This video has been deleted.'
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group("id")
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- self.report_extraction(video_id)
-
- # Extract video URL
- video_url = compat_urllib_parse.unquote(
- self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
-
- # Extract title
+ video_url = compat_urllib_parse.unquote(self._search_regex(
+ r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
video_title = self._html_search_regex(
r'<title>(.*?)</title', webpage, 'title')
-
- # Extract video thumbnail
video_thumbnail = self._search_regex(
r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
@@ -47,14 +37,12 @@ class MalemotionIE(InfoExtractor):
'format_id': 'mp4',
'preference': 1,
}]
+ self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
- 'uploader': None,
- 'upload_date': None,
'title': video_title,
'thumbnail': video_thumbnail,
- 'description': None,
'age_limit': 18,
}
diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 858c1c0c3..8bc333b02 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -3,10 +3,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_parse_qs,
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
index 807b1dc89..d354702d1 100644
--- a/youtube_dl/extractor/mit.py
+++ b/youtube_dl/extractor/mit.py
@@ -5,8 +5,10 @@ import json
from .common import InfoExtractor
from .youtube import YoutubeIE
-from ..utils import (
+from ..compat import (
compat_urlparse,
+)
+from ..utils import (
clean_html,
ExtractorError,
get_element_by_id,
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index 6691521e5..256758323 100644
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -1,12 +1,13 @@
from __future__ import unicode_literals
-import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urlparse,
+)
+from ..utils import (
get_element_by_attribute,
parse_duration,
strip_jsonp,
@@ -15,7 +16,7 @@ from ..utils import (
class MiTeleIE(InfoExtractor):
IE_NAME = 'mitele.es'
- _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/'
+ _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
_TEST = {
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
@@ -31,12 +32,10 @@ class MiTeleIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- episode = mobj.group('episode')
+ episode = self._match_id(url)
webpage = self._download_webpage(url, episode)
embed_data_json = self._search_regex(
- r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
- flags=re.DOTALL
+ r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
).replace('\'', '"')
embed_data = json.loads(embed_data_json)
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index 55cc33a3e..07d194562 100644
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -3,8 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
+)
+from ..utils import (
ExtractorError,
HEADRequest,
int_or_none,
diff --git a/youtube_dl/extractor/moevideo.py b/youtube_dl/extractor/moevideo.py
index 2ff79b9b8..184f9c2c9 100644
--- a/youtube_dl/extractor/moevideo.py
+++ b/youtube_dl/extractor/moevideo.py
@@ -5,10 +5,12 @@ import json
import re
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
+ ExtractorError,
int_or_none,
)
diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py
index d658647e6..2cec12d35 100644
--- a/youtube_dl/extractor/mofosex.py
+++ b/youtube_dl/extractor/mofosex.py
@@ -4,7 +4,7 @@ import os
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
@@ -12,7 +12,7 @@ from ..utils import (
class MofosexIE(InfoExtractor):
- _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
_TEST = {
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
@@ -26,7 +26,7 @@ class MofosexIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
+ video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py
index 1c4f589cc..5de719bdc 100644
--- a/youtube_dl/extractor/moniker.py
+++ b/youtube_dl/extractor/moniker.py
@@ -5,7 +5,7 @@ import os.path
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
@@ -37,10 +37,9 @@ class MonikerIE(InfoExtractor):
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
orig_webpage = self._download_webpage(url, video_id)
+
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py
index 34a4bec3a..9f2853fa3 100644
--- a/youtube_dl/extractor/mooshare.py
+++ b/youtube_dl/extractor/mooshare.py
@@ -4,11 +4,13 @@ import re
import time
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_request,
compat_urllib_parse,
)
+from ..utils import (
+ ExtractorError,
+)
class MooshareIE(InfoExtractor):
@@ -43,9 +45,7 @@ class MooshareIE(InfoExtractor):
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
page = self._download_webpage(url, video_id, 'Downloading page')
if re.search(r'>Video Not Found or Deleted<', page) is not None:
diff --git a/youtube_dl/extractor/motorsport.py b/youtube_dl/extractor/motorsport.py
index 7c0ec6a12..f5ca74e97 100644
--- a/youtube_dl/extractor/motorsport.py
+++ b/youtube_dl/extractor/motorsport.py
@@ -3,13 +3,14 @@ from __future__ import unicode_literals
import hashlib
import json
-import re
import time
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_parse_qs,
compat_str,
+)
+from ..utils import (
int_or_none,
)
@@ -32,10 +33,9 @@ class MotorsportIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('id')
-
+ display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
+
flashvars_code = self._html_search_regex(
r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
flashvars = compat_parse_qs(flashvars_code)
diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py
index 456807dd1..04e17d055 100644
--- a/youtube_dl/extractor/movieclips.py
+++ b/youtube_dl/extractor/movieclips.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_str,
+)
from ..utils import (
ExtractorError,
- compat_str,
clean_html,
)
diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index b482d6d4d..5ebc78033 100644
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py
index 51e540814..5b9b9fbcd 100644
--- a/youtube_dl/extractor/myspass.py
+++ b/youtube_dl/extractor/myspass.py
@@ -2,9 +2,10 @@ from __future__ import unicode_literals
import os.path
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
-
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py
index fbe34defd..c10405f04 100644
--- a/youtube_dl/extractor/naver.py
+++ b/youtube_dl/extractor/naver.py
@@ -4,8 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
+)
+from ..utils import (
ExtractorError,
clean_html,
)
@@ -26,9 +28,9 @@ class NaverIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group(1)
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+
m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
webpage)
if m_id is None:
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index bf5132721..690c46b6a 100644
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -4,8 +4,10 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
+)
+from ..utils import (
ExtractorError,
find_xpath_attr,
)
diff --git a/youtube_dl/extractor/nfb.py b/youtube_dl/extractor/nfb.py
index 7ce1d481d..ea077254b 100644
--- a/youtube_dl/extractor/nfb.py
+++ b/youtube_dl/extractor/nfb.py
@@ -1,9 +1,7 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
compat_urllib_parse,
)
@@ -12,7 +10,7 @@ from ..utils import (
class NFBIE(InfoExtractor):
IE_NAME = 'nfb'
IE_DESC = 'National Film Board of Canada'
- _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+ _VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
_TEST = {
'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
@@ -32,10 +30,10 @@ class NFBIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+ video_id = self._match_id(url)
+ page = self._download_webpage(
+ 'https://www.nfb.ca/film/%s' % video_id, video_id,
+ 'Downloading film page')
uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
page, 'director id', fatal=False)
diff --git a/youtube_dl/extractor/nfl.py b/youtube_dl/extractor/nfl.py
index cc7c921c3..606e2294e 100644
--- a/youtube_dl/extractor/nfl.py
+++ b/youtube_dl/extractor/nfl.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_parse_urlparse,
+)
from ..utils import (
ExtractorError,
- compat_urllib_parse_urlparse,
int_or_none,
remove_end,
)
diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py
index 1d9c1a096..4c1890416 100644
--- a/youtube_dl/extractor/niconico.py
+++ b/youtube_dl/extractor/niconico.py
@@ -5,14 +5,16 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
- unified_strdate,
- parse_duration,
- int_or_none,
+)
+from ..utils import (
ExtractorError,
+ int_or_none,
+ parse_duration,
+ unified_strdate,
)
diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py
index 7d2ff7b9a..251e6da07 100644
--- a/youtube_dl/extractor/noco.py
+++ b/youtube_dl/extractor/noco.py
@@ -6,13 +6,15 @@ import time
import hashlib
from .common import InfoExtractor
-from ..utils import (
- compat_urllib_request,
+from ..compat import (
+ compat_str,
compat_urllib_parse,
- ExtractorError,
+ compat_urllib_request,
+)
+from ..utils import (
clean_html,
+ ExtractorError,
unified_strdate,
- compat_str,
)
diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py
index f3be8f552..f5ef856db 100644
--- a/youtube_dl/extractor/nosvideo.py
+++ b/youtube_dl/extractor/nosvideo.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+)
from ..utils import (
ExtractorError,
- compat_urllib_request,
urlencode_postdata,
xpath_text,
xpath_with_ns,
@@ -32,8 +34,7 @@ class NosVideoIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
fields = {
'id': video_id,
diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py
index 38d05e466..04d779890 100644
--- a/youtube_dl/extractor/novamov.py
+++ b/youtube_dl/extractor/novamov.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urlparse,
+)
from ..utils import (
ExtractorError,
- compat_urlparse
)
diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py
index 449c8a6a3..57928f2ae 100644
--- a/youtube_dl/extractor/nuvid.py
+++ b/youtube_dl/extractor/nuvid.py
@@ -3,15 +3,17 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+)
from ..utils import (
parse_duration,
unified_strdate,
- compat_urllib_request,
)
class NuvidIE(InfoExtractor):
- _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://m.nuvid.com/video/1310741/',
'md5': 'eab207b7ac4fccfb4e23c86201f11277',
@@ -26,8 +28,7 @@ class NuvidIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
formats = []
diff --git a/youtube_dl/extractor/photobucket.py b/youtube_dl/extractor/photobucket.py
index b4389e0b6..c66db3cdc 100644
--- a/youtube_dl/extractor/photobucket.py
+++ b/youtube_dl/extractor/photobucket.py
@@ -4,16 +4,17 @@ import json
import re
from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..compat import compat_urllib_parse
class PhotobucketIE(InfoExtractor):
_VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
_TEST = {
'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
- 'file': 'zpsc0c3b9fa.mp4',
'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
'info_dict': {
+ 'id': 'zpsc0c3b9fa',
+ 'ext': 'mp4',
'timestamp': 1367669341,
'upload_date': '20130504',
'uploader': 'rachaneronas',
diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py
index 17880471d..449d4836c 100644
--- a/youtube_dl/extractor/played.py
+++ b/youtube_dl/extractor/played.py
@@ -5,11 +5,13 @@ import re
import os.path
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
+from ..utils import (
+ ExtractorError,
+)
class PlayedIE(InfoExtractor):
@@ -28,7 +30,6 @@ class PlayedIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
-
orig_webpage = self._download_webpage(url, video_id)
m_error = re.search(
diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py
index ebc046804..9576aed0e 100644
--- a/youtube_dl/extractor/playfm.py
+++ b/youtube_dl/extractor/playfm.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py
index cd3905acb..c3e667e9e 100644
--- a/youtube_dl/extractor/playvid.py
+++ b/youtube_dl/extractor/playvid.py
@@ -3,31 +3,31 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_parse,
+)
from ..utils import (
- ExtractorError,
clean_html,
- compat_urllib_parse,
+ ExtractorError,
)
class PlayvidIE(InfoExtractor):
- _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
+ _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
_TEST = {
- 'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
- 'md5': '44930f8afa616efdf9482daf4fe53e1e',
+ 'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
+ 'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
'info_dict': {
- 'id': 'agbDDi7WZTV',
+ 'id': 'RnmBNgtrrJu',
'ext': 'mp4',
- 'title': 'Michelle Lewin in Miami Beach',
- 'duration': 240,
+ 'title': 'md5:9256d01c6317e3f703848b5906880dc8',
+ 'duration': 82,
'age_limit': 18,
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m_error = re.search(
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 2ca15b717..634142d0d 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -4,10 +4,12 @@ import os
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+ compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
- compat_urllib_parse,
+)
+from ..utils import (
str_to_int,
)
from ..aes import (
@@ -16,7 +18,7 @@ from ..aes import (
class PornHubIE(InfoExtractor):
- _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
+ _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
_TEST = {
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': '882f488fa1f0026f023f33576004a2ed',
diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py
index 7fcde086c..f536e6e6c 100644
--- a/youtube_dl/extractor/promptfile.py
+++ b/youtube_dl/extractor/promptfile.py
@@ -4,12 +4,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
- determine_ext,
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
+from ..utils import (
+ determine_ext,
+ ExtractorError,
+)
class PromptFileIE(InfoExtractor):
diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py
index 1262793c8..385681d06 100644
--- a/youtube_dl/extractor/prosiebensat1.py
+++ b/youtube_dl/extractor/prosiebensat1.py
@@ -5,8 +5,10 @@ import re
from hashlib import sha1
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
+)
+from ..utils import (
unified_strdate,
)
diff --git a/youtube_dl/extractor/quickvid.py b/youtube_dl/extractor/quickvid.py
index 3bc78060d..af7d76cf4 100644
--- a/youtube_dl/extractor/quickvid.py
+++ b/youtube_dl/extractor/quickvid.py
@@ -3,8 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
+)
+from ..utils import (
determine_ext,
int_or_none,
)
diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py
index 2d39ecfe4..aa26b7e0b 100644
--- a/youtube_dl/extractor/rai.py
+++ b/youtube_dl/extractor/rai.py
@@ -3,10 +3,12 @@ from __future__ import unicode_literals
import re
from .subtitles import SubtitlesInfoExtractor
+from ..compat import (
+ compat_urllib_parse,
+)
from ..utils import (
parse_duration,
unified_strdate,
- compat_urllib_parse,
)
diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py
index dc59a5e5c..5e84c1098 100644
--- a/youtube_dl/extractor/rts.py
+++ b/youtube_dl/extractor/rts.py
@@ -4,12 +4,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_str,
+)
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
unescapeHTML,
- compat_str,
)
diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py
index 6941d96fb..b72b5a586 100644
--- a/youtube_dl/extractor/rutube.py
+++ b/youtube_dl/extractor/rutube.py
@@ -5,10 +5,12 @@ import re
import itertools
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
- unified_strdate,
+)
+from ..utils import (
ExtractorError,
+ unified_strdate,
)
@@ -36,9 +38,7 @@ class RutubeIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
video = self._download_json(
'http://rutube.ru/api/video/%s/?format=json' % video_id,
video_id, 'Downloading video JSON')
@@ -114,8 +114,7 @@ class RutubeMovieIE(RutubeChannelIE):
_PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- movie_id = mobj.group('id')
+ movie_id = self._match_id(url)
movie = self._download_json(
self._MOVIE_TEMPLATE % movie_id, movie_id,
'Downloading movie JSON')
diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py
index c145f6fc7..dfd897ba3 100644
--- a/youtube_dl/extractor/screencast.py
+++ b/youtube_dl/extractor/screencast.py
@@ -1,14 +1,14 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_parse_qs,
compat_urllib_request,
)
+from ..utils import (
+ ExtractorError,
+)
class ScreencastIE(InfoExtractor):
@@ -57,8 +57,7 @@ class ScreencastIE(InfoExtractor):
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index fdc31603a..26ced716e 100644
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -4,10 +4,12 @@ import re
import base64
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_parse,
+ compat_urllib_request,
+)
from ..utils import (
ExtractorError,
- compat_urllib_request,
- compat_urllib_parse,
int_or_none,
)
@@ -26,26 +28,30 @@ class SharedIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- page = self._download_webpage(url, video_id)
-
- if re.search(r'>File does not exist<', page) is not None:
- raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
- download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page))
+ if '>File does not exist<' in webpage:
+ raise ExtractorError(
+ 'Video %s does not exist' % video_id, expected=True)
- request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form))
+ download_form = dict(re.findall(
+ r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
+ request = compat_urllib_request.Request(
+ url, compat_urllib_parse.urlencode(download_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- video_page = self._download_webpage(request, video_id, 'Downloading video page')
+ video_page = self._download_webpage(
+ request, video_id, 'Downloading video page')
- video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL')
- title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8')
- filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False))
+ video_url = self._html_search_regex(
+ r'data-url="([^"]+)"', video_page, 'video URL')
+ title = base64.b64decode(self._html_search_meta(
+ 'full:title', webpage, 'title')).decode('utf-8')
+ filesize = int_or_none(self._html_search_meta(
+ 'full:size', webpage, 'file size', fatal=False))
thumbnail = self._html_search_regex(
- r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None)
+ r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
return {
'id': video_id,
diff --git a/youtube_dl/extractor/sharesix.py b/youtube_dl/extractor/sharesix.py
index 7531e8325..ac3e3adf2 100644
--- a/youtube_dl/extractor/sharesix.py
+++ b/youtube_dl/extractor/sharesix.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
parse_duration,
)
diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py
index 5eadbb7ea..a63d126d4 100644
--- a/youtube_dl/extractor/sina.py
+++ b/youtube_dl/extractor/sina.py
@@ -4,7 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
compat_urllib_parse,
)
diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py
index 5864b9936..e7d776e7b 100644
--- a/youtube_dl/extractor/slideshare.py
+++ b/youtube_dl/extractor/slideshare.py
@@ -4,8 +4,10 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py
index 646af3cc9..d031fe401 100644
--- a/youtube_dl/extractor/smotri.py
+++ b/youtube_dl/extractor/smotri.py
@@ -7,9 +7,11 @@ import hashlib
import uuid
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
int_or_none,
unified_strdate,
diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py
index c663e56d4..7d3c0e937 100644
--- a/youtube_dl/extractor/sockshare.py
+++ b/youtube_dl/extractor/sockshare.py
@@ -1,13 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
-from ..utils import (
- ExtractorError,
+import re
+
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
determine_ext,
+ ExtractorError,
)
-import re
from .common import InfoExtractor
@@ -27,9 +30,7 @@ class SockshareIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
url = 'http://sockshare.com/file/%s' % video_id
webpage = self._download_webpage(url, video_id)
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index ab9483d2d..5d60c4939 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -5,11 +5,12 @@ import re
import itertools
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
compat_urlparse,
compat_urllib_parse,
-
+)
+from ..utils import (
ExtractorError,
int_or_none,
unified_strdate,
diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py
index 94602e89e..b936202f6 100644
--- a/youtube_dl/extractor/spankwire.py
+++ b/youtube_dl/extractor/spankwire.py
@@ -3,12 +3,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+ compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
- compat_urllib_parse,
- unified_strdate,
+)
+from ..utils import (
str_to_int,
+ unified_strdate,
)
from ..aes import aes_decrypt_text
diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py
index 057ef5251..2f57f5b7c 100644
--- a/youtube_dl/extractor/sportdeutschland.py
+++ b/youtube_dl/extractor/sportdeutschland.py
@@ -4,8 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
parse_iso8601,
)
diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py
index c1178f26d..38176498d 100644
--- a/youtube_dl/extractor/streamcloud.py
+++ b/youtube_dl/extractor/streamcloud.py
@@ -5,7 +5,7 @@ import re
import time
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py
index 778704839..c3ceb5f76 100644
--- a/youtube_dl/extractor/streamcz.py
+++ b/youtube_dl/extractor/streamcz.py
@@ -1,13 +1,7 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
-import re
-import json
-
from .common import InfoExtractor
-from ..compat import (
- compat_str,
-)
from ..utils import (
int_or_none,
)
diff --git a/youtube_dl/extractor/tapely.py b/youtube_dl/extractor/tapely.py
index 283e11350..f1f43d0a7 100644
--- a/youtube_dl/extractor/tapely.py
+++ b/youtube_dl/extractor/tapely.py
@@ -4,10 +4,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+)
from ..utils import (
- ExtractorError,
clean_html,
- compat_urllib_request,
+ ExtractorError,
float_or_none,
parse_iso8601,
)
diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py
index 72160503c..944177426 100644
--- a/youtube_dl/extractor/ted.py
+++ b/youtube_dl/extractor/ted.py
@@ -5,7 +5,7 @@ import re
from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
)
diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py
index e2653d62d..af6ef0033 100644
--- a/youtube_dl/extractor/theplatform.py
+++ b/youtube_dl/extractor/theplatform.py
@@ -4,8 +4,10 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
+)
+from ..utils import (
determine_ext,
ExtractorError,
xpath_with_ns,
diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py
index 66d159e99..9f9e388c5 100644
--- a/youtube_dl/extractor/tlc.py
+++ b/youtube_dl/extractor/tlc.py
@@ -5,7 +5,7 @@ import re
from .common import InfoExtractor
from .brightcove import BrightcoveIE
from .discovery import DiscoveryIE
-from ..utils import compat_urlparse
+from ..compat import compat_urlparse
class TlcIE(DiscoveryIE):
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index 64a1e9030..d73ad3762 100644
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -4,9 +4,11 @@ import json
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
+)
+from ..utils import (
int_or_none,
str_to_int,
)
diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py
index d516b6427..4de0aac52 100644
--- a/youtube_dl/extractor/tutv.py
+++ b/youtube_dl/extractor/tutv.py
@@ -1,10 +1,9 @@
from __future__ import unicode_literals
import base64
-import re
from .common import InfoExtractor
-from ..utils import compat_parse_qs
+from ..compat import compat_parse_qs
class TutvIE(InfoExtractor):
@@ -20,10 +19,9 @@ class TutvIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+
internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
data_content = self._download_webpage(
diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py
index 397d167e8..715f9930c 100644
--- a/youtube_dl/extractor/twitch.py
+++ b/youtube_dl/extractor/twitch.py
@@ -5,9 +5,11 @@ import itertools
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
parse_iso8601,
)
diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 5271611ac..4667ed83b 100644
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/urort.py b/youtube_dl/extractor/urort.py
index 249a34c86..8872cfcb2 100644
--- a/youtube_dl/extractor/urort.py
+++ b/youtube_dl/extractor/urort.py
@@ -1,11 +1,11 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
+)
+from ..utils import (
unified_strdate,
)
diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py
index 53dc3a496..68d03b999 100644
--- a/youtube_dl/extractor/ustream.py
+++ b/youtube_dl/extractor/ustream.py
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
)
diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
index 455b6d9da..dd026748d 100644
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -1,19 +1,18 @@
# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
-
+)
+from ..utils import (
ExtractorError,
)
class Vbox7IE(InfoExtractor):
- _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)'
+ _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
_TEST = {
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
@@ -25,8 +24,7 @@ class Vbox7IE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
redirect_page, urlh = self._download_webpage_handle(url, video_id)
new_location = self._search_regex(r'window\.location = \'(.*)\';',
diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py
index 94647d1c8..815f58468 100644
--- a/youtube_dl/extractor/veehd.py
+++ b/youtube_dl/extractor/veehd.py
@@ -4,10 +4,12 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
- get_element_by_id,
+)
+from ..utils import (
clean_html,
+ get_element_by_id,
)
@@ -26,8 +28,7 @@ class VeeHDIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
# VeeHD seems to send garbage on the first request.
# See https://github.com/rg3/youtube-dl/issues/2102
diff --git a/youtube_dl/extractor/veoh.py b/youtube_dl/extractor/veoh.py
index a7953a7e7..01e258e32 100644
--- a/youtube_dl/extractor/veoh.py
+++ b/youtube_dl/extractor/veoh.py
@@ -4,8 +4,10 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
int_or_none,
ExtractorError,
)
diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py
index c912c3cbe..43f6b029d 100644
--- a/youtube_dl/extractor/vevo.py
+++ b/youtube_dl/extractor/vevo.py
@@ -4,8 +4,10 @@ import re
import xml.etree.ElementTree
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
)
diff --git a/youtube_dl/extractor/videodetective.py b/youtube_dl/extractor/videodetective.py
index ac6c25537..0ffc7ff7d 100644
--- a/youtube_dl/extractor/videodetective.py
+++ b/youtube_dl/extractor/videodetective.py
@@ -1,10 +1,8 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
+from ..compat import compat_urlparse
from .internetvideoarchive import InternetVideoArchiveIE
-from ..utils import compat_urlparse
class VideoDetectiveIE(InfoExtractor):
@@ -17,13 +15,12 @@ class VideoDetectiveIE(InfoExtractor):
'ext': 'mp4',
'title': 'KICK-ASS 2',
'description': 'md5:65ba37ad619165afac7d432eaded6013',
- 'duration': 135,
+ 'duration': 138,
},
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
og_video = self._og_search_video_url(webpage)
query = compat_urlparse.urlparse(og_video).query
diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py
index 29c4e0101..7a78f0d26 100644
--- a/youtube_dl/extractor/videomega.py
+++ b/youtube_dl/extractor/videomega.py
@@ -1,11 +1,11 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
+)
+from ..utils import (
remove_start,
)
@@ -27,9 +27,7 @@ class VideoMegaIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
webpage = self._download_webpage(url, video_id)
diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
index ca6b0d5b3..542e9198a 100644
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -5,14 +5,17 @@ import re
import json
from .common import InfoExtractor
+from ..compat import (
+ compat_str,
+ compat_urllib_parse,
+ compat_urllib_request,
+)
from ..utils import (
ExtractorError,
- compat_urllib_request,
- compat_urllib_parse,
- compat_str,
+ orderedSet,
unescapeHTML,
unified_strdate,
- orderedSet)
+)
class VKIE(InfoExtractor):
diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py
index affef6507..1c0966a79 100644
--- a/youtube_dl/extractor/vodlocker.py
+++ b/youtube_dl/extractor/vodlocker.py
@@ -2,8 +2,9 @@
from __future__ import unicode_literals
import re
+
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
@@ -24,8 +25,7 @@ class VodlockerIE(InfoExtractor):
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
fields = dict(re.findall(r'''(?x)<input\s+
diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py
index 1b2f731e9..405cb9db4 100644
--- a/youtube_dl/extractor/vube.py
+++ b/youtube_dl/extractor/vube.py
@@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_str,
+)
from ..utils import (
int_or_none,
- compat_str,
ExtractorError,
)
diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py
index ec3c010ad..c3fde53f5 100644
--- a/youtube_dl/extractor/vuclip.py
+++ b/youtube_dl/extractor/vuclip.py
@@ -3,8 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
+)
+from ..utils import (
ExtractorError,
parse_duration,
qualities,
@@ -25,10 +27,9 @@ class VuClipIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+
ad_m = re.search(
r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage)
if ad_m:
diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index 93a6e6454..8e25ecf28 100644
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_parse_qs,
compat_urlparse,
+)
+from ..utils import (
determine_ext,
unified_strdate,
)
@@ -141,7 +143,6 @@ class WDRMobileIE(InfoExtractor):
'title': mobj.group('title'),
'age_limit': int(mobj.group('age_limit')),
'url': url,
- 'ext': determine_ext(url),
'user_agent': 'mobile',
}
diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py
index 748443f81..13a079151 100644
--- a/youtube_dl/extractor/wistia.py
+++ b/youtube_dl/extractor/wistia.py
@@ -1,9 +1,8 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import ExtractorError, compat_urllib_request
+from ..compat import compat_urllib_request
+from ..utils import ExtractorError
class WistiaIE(InfoExtractor):
@@ -22,8 +21,7 @@ class WistiaIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
request = compat_urllib_request.Request(self._API_URL.format(video_id))
request.add_header('Referer', url) # Some videos require this.
diff --git a/youtube_dl/extractor/xbef.py b/youtube_dl/extractor/xbef.py
index 1b4e88365..80c48c37d 100644
--- a/youtube_dl/extractor/xbef.py
+++ b/youtube_dl/extractor/xbef.py
@@ -1,9 +1,7 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
@@ -23,10 +21,9 @@ class XBefIE(InfoExtractor):
}
def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+
title = self._html_search_regex(
r'<h1[^>]*>(.*?)</h1>', webpage, 'title')
diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py
index 53ed7ef5a..79ed6c744 100644
--- a/youtube_dl/extractor/xnxx.py
+++ b/youtube_dl/extractor/xnxx.py
@@ -1,10 +1,8 @@
# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
)
@@ -23,10 +21,7 @@ class XNXXIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- # Get webpage content
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(r'flv_url=(.*?)&amp;',
diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py
index 38448e7c0..f9d98b83f 100644
--- a/youtube_dl/extractor/xtube.py
+++ b/youtube_dl/extractor/xtube.py
@@ -4,15 +4,17 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+)
+from ..utils import (
parse_duration,
str_to_int,
)
class XTubeIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&]+))'
_TEST = {
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
@@ -29,7 +31,7 @@ class XTubeIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
+ video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py
index 7e0044824..2a45dc574 100644
--- a/youtube_dl/extractor/xvideos.py
+++ b/youtube_dl/extractor/xvideos.py
@@ -3,15 +3,17 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
- ExtractorError,
+)
+from ..utils import (
clean_html,
+ ExtractorError,
)
class XVideosIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+ _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
_TEST = {
'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
@@ -24,37 +26,25 @@ class XVideosIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group(1)
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- self.report_extraction(video_id)
-
mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
if mobj:
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
- # Extract video URL
video_url = compat_urllib_parse.unquote(
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
-
- # Extract title
video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
-
- # Extract video thumbnail
video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': video_url,
- 'uploader': None,
- 'upload_date': None,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
- 'description': None,
'age_limit': 18,
}
diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 0fdb12243..031226f27 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -6,11 +6,13 @@ import json
import re
from .common import InfoExtractor, SearchInfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_parse,
compat_urlparse,
+)
+from ..utils import (
clean_html,
+ ExtractorError,
int_or_none,
)
diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py
index 7b621a9e3..894678a23 100644
--- a/youtube_dl/extractor/ynet.py
+++ b/youtube_dl/extractor/ynet.py
@@ -5,7 +5,7 @@ import re
import json
from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..compat import compat_urllib_parse
class YnetIE(InfoExtractor):
diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index d9c06a2ee..107c9ac36 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -6,10 +6,11 @@ import re
import sys
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
-
+)
+from ..utils import (
ExtractorError,
unescapeHTML,
unified_strdate,
diff --git a/youtube_dl/swfinterp.py b/youtube_dl/swfinterp.py
index 2bd264b30..e60505ace 100644
--- a/youtube_dl/swfinterp.py
+++ b/youtube_dl/swfinterp.py
@@ -4,8 +4,8 @@ import collections
import io
import zlib
+from .compat import compat_str
from .utils import (
- compat_str,
ExtractorError,
struct_unpack,
)