aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py5
-rw-r--r--youtube_dl/extractor/livestream.py22
-rw-r--r--youtube_dl/extractor/nbc.py11
-rw-r--r--youtube_dl/extractor/nytimes.py82
-rw-r--r--youtube_dl/extractor/rutv.py17
-rw-r--r--youtube_dl/utils.py8
6 files changed, 95 insertions, 50 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 41af925cc..1c3a46dd8 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -363,7 +363,10 @@ from .nrk import (
)
from .ntvde import NTVDeIE
from .ntvru import NTVRuIE
-from .nytimes import NYTimesIE
+from .nytimes import (
+ NYTimesIE,
+ NYTimesArticleIE,
+)
from .nuvid import NuvidIE
from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE
diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py
index ec309dadd..6d7733e41 100644
--- a/youtube_dl/extractor/livestream.py
+++ b/youtube_dl/extractor/livestream.py
@@ -194,23 +194,19 @@ class LivestreamIE(InfoExtractor):
# The original version of Livestream uses a different system
class LivestreamOriginalIE(InfoExtractor):
IE_NAME = 'livestream:original'
- _VALID_URL = r'''(?x)https?://www\.livestream\.com/
+ _VALID_URL = r'''(?x)https?://original\.livestream\.com/
(?P<user>[^/]+)/(?P<type>video|folder)
(?:\?.*?Id=|/)(?P<id>.*?)(&|$)
'''
_TESTS = [{
- 'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+ 'url': 'http://original.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
'info_dict': {
'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
},
- 'params': {
- # rtmp
- 'skip_download': True,
- },
}, {
- 'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+ 'url': 'https://original.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
'info_dict': {
'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
},
@@ -221,19 +217,17 @@ class LivestreamOriginalIE(InfoExtractor):
api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
info = self._download_xml(api_url, video_id)
+ # this url is used on mobile devices
+ stream_url = 'http://x{0}x.api.channel.livestream.com/3.0/getstream.json?id={1}'.format(user, video_id)
+ stream_info = self._download_json(stream_url, video_id)
item = info.find('channel').find('item')
ns = {'media': 'http://search.yahoo.com/mrss'}
thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
- # Remove the extension and number from the path (like 1.jpg)
- path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')
return {
'id': video_id,
'title': item.find('title').text,
- 'url': 'rtmp://extondemand.livestream.com/ondemand',
- 'play_path': 'trans/dv15/mogulus-{0}'.format(path),
- 'player_url': 'http://static.livestream.com/chromelessPlayer/v21/playerapi.swf?hash=5uetk&v=0803&classid=D27CDB6E-AE6D-11cf-96B8-444553540000&jsEnabled=false&wmode=opaque',
- 'ext': 'flv',
+ 'url': stream_info['progressiveUrl'],
'thumbnail': thumbnail_url,
}
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index 6cbe03d0f..dc2091be0 100644
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -10,6 +10,8 @@ from ..compat import (
from ..utils import (
ExtractorError,
find_xpath_attr,
+ lowercase_escape,
+ unescapeHTML,
)
@@ -46,18 +48,23 @@ class NBCIE(InfoExtractor):
'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
},
'skip': 'Only works from US',
+ },
+ {
+ # This video has expired but with an escaped embedURL
+ 'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
+ 'skip': 'Expired'
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- theplatform_url = self._search_regex(
+ theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
[
r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
r'"embedURL"\s*:\s*"([^"]+)"'
],
- webpage, 'theplatform url').replace('_no_endcard', '')
+ webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
if theplatform_url.startswith('//'):
theplatform_url = 'http:' + theplatform_url
return self.url_result(theplatform_url)
diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py
index 03f0a4de6..6ffbe3863 100644
--- a/youtube_dl/extractor/nytimes.py
+++ b/youtube_dl/extractor/nytimes.py
@@ -8,30 +8,8 @@ from ..utils import (
)
-class NYTimesIE(InfoExtractor):
- _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
-
- _TESTS = [{
- 'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
- 'md5': '18a525a510f942ada2720db5f31644c0',
- 'info_dict': {
- 'id': '100000002847155',
- 'ext': 'mov',
- 'title': 'Verbatim: What Is a Photocopier?',
- 'description': 'md5:93603dada88ddbda9395632fdc5da260',
- 'timestamp': 1398631707,
- 'upload_date': '20140427',
- 'uploader': 'Brett Weiner',
- 'duration': 419,
- }
- }, {
- 'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
- 'only_matching': True,
- }]
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
+class NYTimesBaseIE(InfoExtractor):
+ def _extract_video_from_id(self, video_id):
video_data = self._download_json(
'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
video_id, 'Downloading video JSON')
@@ -81,3 +59,59 @@ class NYTimesIE(InfoExtractor):
'formats': formats,
'thumbnails': thumbnails,
}
+
+
+class NYTimesIE(NYTimesBaseIE):
+ _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
+
+ _TESTS = [{
+ 'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
+ 'md5': '18a525a510f942ada2720db5f31644c0',
+ 'info_dict': {
+ 'id': '100000002847155',
+ 'ext': 'mov',
+ 'title': 'Verbatim: What Is a Photocopier?',
+ 'description': 'md5:93603dada88ddbda9395632fdc5da260',
+ 'timestamp': 1398631707,
+ 'upload_date': '20140427',
+ 'uploader': 'Brett Weiner',
+ 'duration': 419,
+ }
+ }, {
+ 'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ return self._extract_video_from_id(video_id)
+
+
+class NYTimesArticleIE(NYTimesBaseIE):
+ _VALID_URL = r'https?://(?:www)?\.nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
+ _TESTS = [{
+ 'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
+ 'md5': 'e2076d58b4da18e6a001d53fd56db3c9',
+ 'info_dict': {
+ 'id': '100000003628438',
+ 'ext': 'mov',
+ 'title': 'New Minimum Wage: $70,000 a Year',
+ 'description': 'Dan Price, C.E.O. of Gravity Payments, surprised his 120-person staff by announcing that he planned over the next three years to raise the salary of every employee to $70,000 a year.',
+ 'timestamp': 1429033037,
+ 'upload_date': '20150414',
+ 'uploader': 'Matthew Williams',
+ }
+ }, {
+ 'url': 'http://www.nytimes.com/news/minute/2014/03/17/times-minute-whats-next-in-crimea/?_php=true&_type=blogs&_php=true&_type=blogs&_r=1',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_id = self._html_search_regex(r'data-videoid="(\d+)"', webpage, 'video id')
+
+ return self._extract_video_from_id(video_id)
diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py
index 1ec2c86e5..55604637d 100644
--- a/youtube_dl/extractor/rutv.py
+++ b/youtube_dl/extractor/rutv.py
@@ -87,7 +87,7 @@ class RUTVIE(InfoExtractor):
'skip': 'Translation has finished',
},
{
- 'url': 'http://live.russia.tv/index/index/channel_id/3',
+ 'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/',
'info_dict': {
'id': '21',
'ext': 'mp4',
@@ -128,8 +128,10 @@ class RUTVIE(InfoExtractor):
elif video_path.startswith('index/iframe/cast_id'):
video_type = 'live'
+ is_live = video_type == 'live'
+
json_data = self._download_json(
- 'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id),
+ 'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if is_live else '', video_id),
video_id, 'Downloading JSON')
if json_data['errors']:
@@ -156,6 +158,7 @@ class RUTVIE(InfoExtractor):
for transport, links in media['sources'].items():
for quality, url in links.items():
+ preference = -1 if priority_transport == transport else -2
if transport == 'rtmp':
mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
if not mobj:
@@ -169,9 +172,11 @@ class RUTVIE(InfoExtractor):
'rtmp_live': True,
'ext': 'flv',
'vbr': int(quality),
+ 'preference': preference,
}
elif transport == 'm3u8':
- formats.extend(self._extract_m3u8_formats(url, video_id, 'mp4'))
+ formats.extend(self._extract_m3u8_formats(
+ url, video_id, 'mp4', preference=preference, m3u8_id='hls'))
continue
else:
fmt = {
@@ -181,17 +186,11 @@ class RUTVIE(InfoExtractor):
'width': width,
'height': height,
'format_id': '%s-%s' % (transport, quality),
- 'preference': -1 if priority_transport == transport else -2,
})
formats.append(fmt)
- if not formats:
- raise ExtractorError('No media links available for %s' % video_id)
-
self._sort_formats(formats)
- is_live = video_type == 'live'
-
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index a5a5c317e..1013f7c18 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1486,6 +1486,14 @@ def uppercase_escape(s):
s)
+def lowercase_escape(s):
+ unicode_escape = codecs.getdecoder('unicode_escape')
+ return re.sub(
+ r'\\u[0-9a-fA-F]{4}',
+ lambda m: unicode_escape(m.group(0))[0],
+ s)
+
+
def escape_rfc3986(s):
"""Escape non-ASCII characters as suggested by RFC 3986"""
if sys.version_info < (3, 0) and isinstance(s, compat_str):
generated by cgit v1.2.3 (git 2.26.2) at 2024-11-01 00:50:57 +0000