--- /dev/null
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_http_server
+import ssl
+import threading
+
+TEST_DIR = os.path.dirname(os.path.abspath(__file__))
+
+
+class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+ def log_message(self, format, *args):
+ pass
+
+ def do_GET(self):
+ if self.path == '/video.html':
+ self.send_response(200)
+ self.send_header('Content-Type', 'text/html; charset=utf-8')
+ self.end_headers()
+ self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
+ elif self.path == '/vid.mp4':
+ self.send_response(200)
+ self.send_header('Content-Type', 'video/mp4')
+ self.end_headers()
+ self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
+ else:
+ assert False
+
+
+class FakeLogger(object):
+ def debug(self, msg):
+ pass
+
+ def warning(self, msg):
+ pass
+
+ def error(self, msg):
+ pass
+
+
+class TestHTTP(unittest.TestCase):
+ def setUp(self):
+ certfn = os.path.join(TEST_DIR, 'testcert.pem')
+ self.httpd = compat_http_server.HTTPServer(
+ ('localhost', 0), HTTPTestRequestHandler)
+ self.httpd.socket = ssl.wrap_socket(
+ self.httpd.socket, certfile=certfn, server_side=True)
+ self.port = self.httpd.socket.getsockname()[1]
+ self.server_thread = threading.Thread(target=self.httpd.serve_forever)
+ self.server_thread.daemon = True
+ self.server_thread.start()
+
+ def test_nocheckcertificate(self):
+ if sys.version_info >= (2, 7, 9): # No certificate checking anyways
+ ydl = YoutubeDL({'logger': FakeLogger()})
+ self.assertRaises(
+ Exception,
+ ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
+
+ ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
+ r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
+ self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
+
+if __name__ == '__main__':
+ unittest.main()
--- /dev/null
+-----BEGIN PRIVATE KEY-----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+-----END PRIVATE KEY-----
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
if thumbnails is None:
thumbnail = info_dict.get('thumbnail')
if thumbnail:
- thumbnails = [{'url': thumbnail}]
+ info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
if thumbnails:
thumbnails.sort(key=lambda t: (
t.get('preference'), t.get('width'), t.get('height'),
sys.exit()
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
- parser.error('you must provide at least one URL')
+ parser.error(
+ 'You must provide at least one URL.\n'
+ 'Type youtube-dl --help to see a list of all options.')
try:
if opts.load_info_filename is not None:
except ImportError:
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+try:
+ import http.server as compat_http_server
+except ImportError:
+ import BaseHTTPServer as compat_http_server
+
try:
from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
'compat_html_entities',
'compat_html_parser',
'compat_http_client',
+ 'compat_http_server',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
CrunchyrollShowPlaylistIE
)
from .cspan import CSpanIE
+from .ctsnews import CtsNewsIE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
from .xnxx import XNXXIE
from .xvideos import XVideosIE
from .xtube import XTubeUserIE, XTubeIE
+from .xuite import XuiteIE
from .xxxymovies import XXXYMoviesIE
from .yahoo import (
YahooIE,
--- /dev/null
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import parse_iso8601, ExtractorError
+
+
+class CtsNewsIE(InfoExtractor):
+ # https connection failed (Connection reset)
+ _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
+ _TESTS = [{
+ 'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
+ 'md5': 'a9875cb790252b08431186d741beaabe',
+ 'info_dict': {
+ 'id': '201501291578109',
+ 'ext': 'mp4',
+ 'title': '以色列.真主黨交火 3人死亡',
+ 'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
+ 'timestamp': 1422528540,
+ 'upload_date': '20150129',
+ }
+ }, {
+ # News count not appear on page but still available in database
+ 'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html',
+ 'md5': '3aee7e0df7cdff94e43581f54c22619e',
+ 'info_dict': {
+ 'id': '201309031304098',
+ 'ext': 'mp4',
+ 'title': '韓國31歲童顏男 貌如十多歲小孩',
+ 'description': 'md5:f183feeba3752b683827aab71adad584',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'timestamp': 1378205880,
+ 'upload_date': '20130903',
+ }
+ }, {
+ # With Youtube embedded video
+ 'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
+ 'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
+ 'add_ie': ['Youtube'],
+ 'info_dict': {
+ 'id': 'OVbfO7d0_hQ',
+ 'ext': 'mp4',
+ 'title': 'iPhone6熱銷 蘋果財報亮眼',
+ 'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'upload_date': '20150128',
+ 'uploader_id': 'TBSCTS',
+ 'uploader': '中華電視公司',
+ }
+ }]
+
+ def _real_extract(self, url):
+ news_id = self._match_id(url)
+ page = self._download_webpage(url, news_id)
+
+ if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
+ feed_url = self._html_search_regex(
+ r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
+ page, 'feed url')
+ video_url = self._download_webpage(
+ feed_url, news_id, note='Fetching feed')
+ else:
+ self.to_screen('Not CTSPlayer video, trying Youtube...')
+ youtube_url = self._search_regex(
+ r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
+ default=None)
+ if not youtube_url:
+ raise ExtractorError('The news includes no videos!', expected=True)
+
+ return {
+ '_type': 'url',
+ 'url': youtube_url,
+ 'ie_key': 'Youtube',
+ }
+
+ description = self._html_search_meta('description', page)
+ title = self._html_search_meta('title', page)
+ thumbnail = self._html_search_meta('image', page)
+
+ datetime_str = self._html_search_regex(
+ r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
+ # Transform into ISO 8601 format with timezone info
+ datetime_str = datetime_str.replace('/', '-') + ':00+0800'
+ timestamp = parse_iso8601(datetime_str, delimiter=' ')
+
+ return {
+ 'id': news_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ }
class SRMediathekIE(InfoExtractor):
- IE_DESC = 'Süddeutscher Rundfunk'
+ IE_DESC = 'Saarländischer Rundfunk'
_VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
_TEST = {
int_or_none,
)
from ..compat import (
- compat_urllib_request
+ compat_urllib_request
)
--- /dev/null
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import base64
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+from ..utils import (
+ ExtractorError,
+ parse_iso8601,
+ parse_duration,
+)
+
+
+class XuiteIE(InfoExtractor):
+ _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
+ _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
+ _TESTS = [{
+ # Audio
+ 'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
+ 'md5': '63a42c705772aa53fd4c1a0027f86adf',
+ 'info_dict': {
+ 'id': '3860914',
+ 'ext': 'mp3',
+ 'title': '孤單南半球-歐德陽',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 247.246,
+ 'timestamp': 1314932940,
+ 'upload_date': '20110902',
+ 'uploader': '阿能',
+ 'uploader_id': '15973816',
+ 'categories': ['個人短片'],
+ },
+ }, {
+ # Video with only one format
+ 'url': 'http://vlog.xuite.net/play/TkRZNjhULTM0NDE2MjkuZmx2',
+ 'md5': 'c45737fc8ac5dc8ac2f92ecbcecf505e',
+ 'info_dict': {
+ 'id': '3441629',
+ 'ext': 'mp4',
+ 'title': '孫燕姿 - 眼淚成詩',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 217.399,
+ 'timestamp': 1299383640,
+ 'upload_date': '20110306',
+ 'uploader': 'Valen',
+ 'uploader_id': '10400126',
+ 'categories': ['影視娛樂'],
+ },
+ }, {
+ # Video with two formats
+ 'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==',
+ 'md5': '1166e0f461efe55b62e26a2d2a68e6de',
+ 'info_dict': {
+ 'id': '21301170',
+ 'ext': 'mp4',
+ 'title': '暗殺教室 02',
+ 'description': '字幕:【極影字幕社】',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 1384.907,
+ 'timestamp': 1421481240,
+ 'upload_date': '20150117',
+ 'uploader': '我只是想認真點',
+ 'uploader_id': '242127761',
+ 'categories': ['電玩動漫'],
+ },
+ }, {
+ 'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
+ 'only_matching': True,
+ }]
+
+ def _extract_flv_config(self, media_id):
+ base64_media_id = base64.b64encode(media_id.encode('utf-8')).decode('utf-8')
+ flv_config = self._download_xml(
+ 'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id,
+ 'flv config')
+ prop_dict = {}
+ for prop in flv_config.findall('./property'):
+ prop_id = base64.b64decode(prop.attrib['id']).decode('utf-8')
+ # CDATA may be empty in flv config
+ if not prop.text:
+ continue
+ encoded_content = base64.b64decode(prop.text).decode('utf-8')
+ prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
+ return prop_dict
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ error_msg = self._search_regex(
+ r'<div id="error-message-content">([^<]+)',
+ webpage, 'error message', default=None)
+ if error_msg:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, error_msg),
+ expected=True)
+
+ video_id = self._html_search_regex(
+ r'data-mediaid="(\d+)"', webpage, 'media id')
+ flv_config = self._extract_flv_config(video_id)
+
+ FORMATS = {
+ 'audio': 'mp3',
+ 'video': 'mp4',
+ }
+
+ formats = []
+ for format_tag in ('src', 'hq_src'):
+ video_url = flv_config.get(format_tag)
+ if not video_url:
+ continue
+ format_id = self._search_regex(
+ r'\bq=(.+?)\b', video_url, 'format id', default=format_tag)
+ formats.append({
+ 'url': video_url,
+ 'ext': FORMATS.get(flv_config['type'], 'mp4'),
+ 'format_id': format_id,
+ 'height': int(format_id) if format_id.isnumeric() else None,
+ })
+ self._sort_formats(formats)
+
+ timestamp = flv_config.get('publish_datetime')
+ if timestamp:
+ timestamp = parse_iso8601(timestamp + ' +0800', ' ')
+
+ category = flv_config.get('category')
+ categories = [category] if category else []
+
+ return {
+ 'id': video_id,
+ 'title': flv_config['title'],
+ 'description': flv_config.get('description'),
+ 'thumbnail': flv_config.get('thumb'),
+ 'timestamp': timestamp,
+ 'uploader': flv_config.get('author_name'),
+ 'uploader_id': flv_config.get('author_id'),
+ 'duration': parse_duration(flv_config.get('duration')),
+ 'categories': categories,
+ 'formats': formats,
+ }
self._params = params
def https_open(self, req):
+ kwargs = {}
+ if hasattr(self, '_context'): # python > 2.6
+ kwargs['context'] = self._context
+ if hasattr(self, '_check_hostname'): # python 3.x
+ kwargs['check_hostname'] = self._check_hostname
return self.do_open(functools.partial(
_create_http_connection, self, self._https_conn_class, True),
- req)
+ req, **kwargs)
def parse_iso8601(date_str, delimiter='T'):
projects / youtube-dl / commitdiff