aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py5
-rw-r--r--youtube_dl/extractor/crunchyroll.py6
-rw-r--r--youtube_dl/extractor/mit.py68
-rw-r--r--youtube_dl/extractor/mixcloud.py2
-rw-r--r--youtube_dl/extractor/nbc.py24
-rw-r--r--youtube_dl/extractor/theplatform.py14
6 files changed, 78 insertions, 41 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index ee081b1f3..e16bbd969 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -152,7 +152,10 @@ from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .naver import NaverIE
from .nba import NBAIE
-from .nbc import NBCNewsIE
+from .nbc import (
+ NBCIE,
+ NBCNewsIE,
+)
from .ndr import NDRIE
from .ndtv import NDTVIE
from .newgrounds import NewgroundsIE
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index 5587ade12..026a9177e 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -86,9 +86,8 @@ class CrunchyrollIE(InfoExtractor):
return zlib.decompress(decrypted_data)
def _convert_subtitles_to_srt(self, subtitles):
- i = 1
output = ''
- for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
+ for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
start = start.replace('.', ',')
end = end.replace('.', ',')
text = clean_html(text)
@@ -96,7 +95,6 @@ class CrunchyrollIE(InfoExtractor):
if not text:
continue
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
- i += 1
return output
def _real_extract(self,url):
@@ -187,4 +185,4 @@ class CrunchyrollIE(InfoExtractor):
'upload_date': video_upload_date,
'subtitles': subtitles,
'formats': formats,
- } \ No newline at end of file
+ }
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
index 7c40cb8bd..f1db3744f 100644
--- a/youtube_dl/extractor/mit.py
+++ b/youtube_dl/extractor/mit.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
import re
import json
@@ -10,16 +12,17 @@ from ..utils import (
class TechTVMITIE(InfoExtractor):
- IE_NAME = u'techtv.mit.edu'
+ IE_NAME = 'techtv.mit.edu'
_VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
_TEST = {
- u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
- u'file': u'25418.mp4',
- u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
- u'info_dict': {
- u'title': u'MIT DNA Learning Center Set',
- u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+ 'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+ 'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
+ 'info_dict': {
+ 'id': '25418',
+ 'ext': 'mp4',
+ 'title': 'MIT DNA Learning Center Set',
+ 'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
},
}
@@ -28,12 +31,12 @@ class TechTVMITIE(InfoExtractor):
video_id = mobj.group('id')
raw_page = self._download_webpage(
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
- clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
+ clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
- base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
- raw_page, u'base url')
- formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
- u'video formats')
+ base_url = self._search_regex(
+ r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
+ formats_json = self._search_regex(
+ r'bitrates: (\[.+?\])', raw_page, 'video formats')
formats_mit = json.loads(formats_json)
formats = [
{
@@ -49,28 +52,32 @@ class TechTVMITIE(InfoExtractor):
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: \'(.+?)\'',
- raw_page, u'thumbnail', flags=re.DOTALL)
-
- return {'id': video_id,
- 'title': title,
- 'formats': formats,
- 'description': description,
- 'thumbnail': thumbnail,
- }
+ thumbnail = self._search_regex(
+ r'playlist:.*?url: \'(.+?)\'',
+ raw_page, 'thumbnail', flags=re.DOTALL)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }
class MITIE(TechTVMITIE):
- IE_NAME = u'video.mit.edu'
+ IE_NAME = 'video.mit.edu'
_VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
_TEST = {
- u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
- u'file': u'21783.mp4',
- u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
- u'info_dict': {
- u'title': u'The Government is Profiling You',
- u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+ 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+ 'file': '.mp4',
+ 'md5': '7db01d5ccc1895fc5010e9c9e13648da',
+ 'info_dict': {
+ 'id': '21783',
+ 'ext': 'mp4',
+ 'title': 'The Government is Profiling You',
+ 'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
},
}
@@ -78,9 +85,8 @@ class MITIE(TechTVMITIE):
mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
- self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
- embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
- u'embed url')
+ embed_url = self._search_regex(
+ r'<iframe .*?src="(.+?)"', webpage, 'embed url')
return self.url_result(embed_url, ie='TechTVMIT')
class OCWMITIE(InfoExtractor):
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index f3356db50..b8d363eb6 100644
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -10,7 +10,7 @@ from ..utils import (
class MixcloudIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
IE_NAME = 'mixcloud'
_TEST = {
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index ff750de3f..1a63ab56a 100644
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -6,6 +6,30 @@ from .common import InfoExtractor
from ..utils import find_xpath_attr, compat_str
+class NBCIE(InfoExtractor):
+ _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)'
+
+ _TEST = {
+ 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
+ 'md5': '54d0fbc33e0b853a65d7b4de5c06d64e',
+ 'info_dict': {
+ 'id': 'u1RInQZRN7QJ',
+ 'ext': 'flv',
+ 'title': 'I Am a Firefighter',
+ 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
+ if theplatform_url.startswith('//'):
+ theplatform_url = 'http:' + theplatform_url
+ return self.url_result(theplatform_url)
+
+
class NBCNewsIE(InfoExtractor):
_VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py
index d60702325..91f2453eb 100644
--- a/youtube_dl/extractor/theplatform.py
+++ b/youtube_dl/extractor/theplatform.py
@@ -13,7 +13,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language
class ThePlatformIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/
- (?P<config>[^/\?]+/(?:swf|config)/select/)?
+ (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
|theplatform:)(?P<id>[^/\?&]+)'''
_TEST = {
@@ -54,10 +54,15 @@ class ThePlatformIE(InfoExtractor):
f4m_node = body.find(_x('smil:seq/smil:video'))
if f4m_node is not None:
+ f4m_url = f4m_node.attrib['src']
+ if 'manifest.f4m?' not in f4m_url:
+ f4m_url += '?'
+ # the parameters are from syfy.com, other sites may use others,
+ # they also work for nbc.com
+ f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3'
formats = [{
'ext': 'flv',
- # the parameters are from syfy.com, other sites may use others
- 'url': f4m_node.attrib['src'] + '?g=UXWGVKRWHFSP&hdcore=3.0.3',
+ 'url': f4m_url,
}]
else:
base_url = head.find(_x('smil:meta')).attrib['base']
@@ -95,9 +100,10 @@ class ThePlatformIE(InfoExtractor):
if mobj.group('config'):
config_url = url+ '&form=json'
config_url = config_url.replace('swf/', 'config/')
+ config_url = config_url.replace('onsite/', 'onsite/config/')
config_json = self._download_webpage(config_url, video_id, u'Downloading config')
config = json.loads(config_json)
- smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4'
+ smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
else:
smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
'format=smil&mbr=true'.format(video_id))