aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorAllan Zhou <allanzp@gmail.com>2013-08-30 17:51:59 -0700
committerAllan Zhou <allanzp@gmail.com>2013-08-30 17:51:59 -0700
commit85f03346ebe38c0b4cd46ab64bf9b5825d12895a (patch)
tree2aa3c34c3380174cbb10df809c7607f26c19b018 /youtube_dl/extractor
parentbdc6b3fc64a03045b8130cdc824ee3f6c15eeff1 (diff)
parent10f5c016ec6262e5d29327e97fe4f3d1127ccdff (diff)
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/common.py2
-rw-r--r--youtube_dl/extractor/ign.py8
-rw-r--r--youtube_dl/extractor/mit.py16
-rw-r--r--youtube_dl/extractor/orf.py67
-rw-r--r--youtube_dl/extractor/unistra.py2
-rw-r--r--youtube_dl/extractor/youtube.py8
7 files changed, 87 insertions, 17 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 6b5037c8c..90f1a4418 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -59,6 +59,7 @@ from .myvideo import MyVideoIE
from .nba import NBAIE
from .nbc import NBCNewsIE
from .ooyala import OoyalaIE
+from .orf import ORFIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
from .pornotube import PornotubeIE
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index a2986cebe..77726ee24 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -150,7 +150,7 @@ class InfoExtractor(object):
if m:
encoding = m.group(1)
else:
- m = re.search(br'<meta[^>]+charset="?([^"]+)[ /">]',
+ m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
webpage_bytes[:1024])
if m:
encoding = m.group(1).decode('ascii')
diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py
index 62abab655..b1c84278a 100644
--- a/youtube_dl/extractor/ign.py
+++ b/youtube_dl/extractor/ign.py
@@ -13,7 +13,7 @@ class IGNIE(InfoExtractor):
Some videos of it.ign.com are also supported
"""
- _VALID_URL = r'https?://.+?\.ign\.com/(?:videos|show_videos)(/.+)?/(?P<name_or_id>.+)'
+ _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles)(/.+)?/(?P<name_or_id>.+)'
IE_NAME = u'ign.com'
_CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
@@ -41,7 +41,11 @@ class IGNIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name_or_id = mobj.group('name_or_id')
+ page_type = mobj.group('type')
webpage = self._download_webpage(url, name_or_id)
+ if page_type == 'articles':
+ video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
+ return self.url_result(video_url, ie='IGN')
video_id = self._find_video_id(webpage)
result = self._get_video_info(video_id)
description = self._html_search_regex(self._DESCRIPTION_RE,
@@ -68,7 +72,7 @@ class IGNIE(InfoExtractor):
class OneUPIE(IGNIE):
"""Extractor for 1up.com, it uses the ign videos system."""
- _VALID_URL = r'https?://gamevideos.1up.com/video/id/(?P<name_or_id>.+)'
+ _VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
IE_NAME = '1up.com'
_DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
index d09d03e36..52be9232f 100644
--- a/youtube_dl/extractor/mit.py
+++ b/youtube_dl/extractor/mit.py
@@ -25,23 +25,21 @@ class TechTVMITIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- webpage = self._download_webpage(
+ raw_page = self._download_webpage(
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
- embed_page = self._download_webpage(
- 'http://techtv.mit.edu/embeds/%s/' % video_id, video_id,
- note=u'Downloading embed page')
+ clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
- embed_page, u'base url')
- formats_json = self._search_regex(r'bitrates: (\[.+?\])', embed_page,
+ raw_page, u'base url')
+ formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
u'video formats')
formats = json.loads(formats_json)
formats = sorted(formats, key=lambda f: f['bitrate'])
- title = get_element_by_id('edit-title', webpage)
- description = clean_html(get_element_by_id('edit-description', webpage))
+ title = get_element_by_id('edit-title', clean_page)
+ description = clean_html(get_element_by_id('edit-description', clean_page))
thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
- embed_page, u'thumbnail', flags=re.DOTALL)
+ raw_page, u'thumbnail', flags=re.DOTALL)
return {'id': video_id,
'title': title,
diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py
new file mode 100644
index 000000000..41ef8e992
--- /dev/null
+++ b/youtube_dl/extractor/orf.py
@@ -0,0 +1,67 @@
+# coding: utf-8
+
+import re
+import xml.etree.ElementTree
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ ExtractorError,
+ find_xpath_attr,
+)
+
+class ORFIE(InfoExtractor):
+ _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://tvthek.orf.at/programs/1171769-Wetter-ZIB/episodes/6557323-Wetter',
+ u'file': u'6566957.flv',
+ u'info_dict': {
+ u'title': u'Wetter',
+ u'description': u'Christa Kummer, Marcus Wadsak und Kollegen präsentieren abwechselnd ihre täglichen Wetterprognosen für Österreich.\r \r Mehr Wetter unter wetter.ORF.at',
+ },
+ u'params': {
+ # It uses rtmp
+ u'skip_download': True,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ playlist_id = mobj.group('id')
+ webpage = self._download_webpage(url, playlist_id)
+
+ flash_xml = self._search_regex('ORF.flashXML = \'(.+?)\'', webpage, u'flash xml')
+ flash_xml = compat_urlparse.parse_qs('xml='+flash_xml)['xml'][0]
+ flash_config = xml.etree.ElementTree.fromstring(flash_xml.encode('utf-8'))
+ playlist_json = self._search_regex(r'playlist\': \'(\[.*?\])\'', webpage, u'playlist').replace(r'\"','"')
+ playlist = json.loads(playlist_json)
+
+ videos = []
+ ns = '{http://tempuri.org/XMLSchema.xsd}'
+ xpath = '%(ns)sPlaylist/%(ns)sItems/%(ns)sItem' % {'ns': ns}
+ webpage_description = self._og_search_description(webpage)
+ for (i, (item, info)) in enumerate(zip(flash_config.findall(xpath), playlist), 1):
+ # Get best quality url
+ rtmp_url = None
+ for q in ['Q6A', 'Q4A', 'Q1A']:
+ video_url = find_xpath_attr(item, '%sVideoUrl' % ns, 'quality', q)
+ if video_url is not None:
+ rtmp_url = video_url.text
+ break
+ if rtmp_url is None:
+ raise ExtractorError(u'Couldn\'t get video url: %s' % info['id'])
+ description = self._html_search_regex(
+ r'id="playlist_entry_%s".*?<p>(.*?)</p>' % i, webpage,
+ u'description', default=webpage_description, flags=re.DOTALL)
+ videos.append({
+ '_type': 'video',
+ 'id': info['id'],
+ 'title': info['title'],
+ 'url': rtmp_url,
+ 'ext': 'flv',
+ 'description': description,
+ })
+
+ return videos
diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py
index 5ba0a9061..516e18914 100644
--- a/youtube_dl/extractor/unistra.py
+++ b/youtube_dl/extractor/unistra.py
@@ -11,7 +11,7 @@ class UnistraIE(InfoExtractor):
u'md5': u'736f605cfdc96724d55bb543ab3ced24',
u'info_dict': {
u'title': u'M!ss Yella',
- u'description': u'md5:75e8439a3e2981cd5d4b6db232e8fdfc',
+ u'description': u'md5:104892c71bd48e55d70b902736b81bbf',
},
}
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index bd2b986ce..d331aa01b 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -346,7 +346,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
u"info_dict": {
u"upload_date": u"20120506",
u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
- u"description": u"md5:b085c9804f5ab69f4adea963a2dceb3c",
+ u"description": u"md5:3e2666e0a55044490499ea45fe9037b7",
u"uploader": u"Icona Pop",
u"uploader_id": u"IconaPop"
}
@@ -434,11 +434,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif len(s) == 87:
return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:]
elif len(s) == 86:
- return s[5:40] + s[3] + s[41:48] + s[0] + s[49:86]
+ return s[81:73:-1] + s[84] + s[72:58:-1] + s[0] + s[57:35:-1] + s[85] + s[34:0:-1]
elif len(s) == 85:
return s[83:34:-1] + s[0] + s[33:27:-1] + s[3] + s[26:19:-1] + s[34] + s[18:3:-1] + s[27]
elif len(s) == 84:
- return s[5:40] + s[3] + s[41:48] + s[0] + s[49:84]
+ return s[81:36:-1] + s[0] + s[35:2:-1]
elif len(s) == 83:
return s[81:64:-1] + s[82] + s[63:52:-1] + s[45] + s[51:45:-1] + s[1] + s[44:1:-1] + s[0]
elif len(s) == 82:
@@ -1184,7 +1184,7 @@ class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = u'youtube:favorites'
IE_DESC = u'YouTube.com favourite videos, "ytfav" keyword (requires authentication)'
- _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:o?rites)?'
+ _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
_LOGIN_REQUIRED = True
def _real_extract(self, url):