3 from __future__
import unicode_literals
7 compat_urllib_parse_unquote
,
14 from .bokecc
import BokeCCBaseIE
17 class InfoQIE(BokeCCBaseIE
):
18 _VALID_URL
= r
'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
21 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
22 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
24 'id': 'A-Few-of-My-Favorite-Python-Things',
26 'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
27 'title': 'A Few of My Favorite [Python] Things',
30 'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
31 'only_matching': True,
33 'url': 'http://www.infoq.com/cn/presentations/openstack-continued-delivery',
34 'md5': '4918d0cca1497f2244572caf626687ef',
36 'id': 'openstack-continued-delivery',
37 'title': 'OpenStack持续交付之路',
39 'description': 'md5:308d981fb28fa42f49f9568322c683ff',
42 'url': 'https://www.infoq.com/presentations/Simple-Made-Easy',
43 'md5': '0e34642d4d9ef44bf86f66f6399672db',
45 'id': 'Simple-Made-Easy',
46 'title': 'Simple Made Easy',
48 'description': 'md5:3e0e213a8bbd074796ef89ea35ada25b',
51 'format': 'bestaudio',
55 def _extract_rtmp_video(self
, webpage
):
56 # The server URL is hardcoded
57 video_url
= 'rtmpe://video.infoq.com/cfx/st/'
60 encoded_id
= self
._search
_regex
(
61 r
"jsclassref\s*=\s*'([^']*)'", webpage
, 'encoded id', default
=None)
63 real_id
= compat_urllib_parse_unquote(compat_b64decode(encoded_id
).decode('utf-8'))
64 playpath
= 'mp4:' + real_id
67 'format_id': 'rtmp_video',
69 'ext': determine_ext(playpath
),
70 'play_path': playpath
,
73 def _extract_cf_auth(self
, webpage
):
74 policy
= self
._search
_regex
(r
'InfoQConstants\.scp\s*=\s*\'([^
\']+)\'', webpage, 'policy
')
75 signature = self._search_regex(r'InfoQConstants\
.scs\s
*=\s
*\'([^
\']+)\'', webpage, 'signature
')
76 key_pair_id = self._search_regex(r'InfoQConstants\
.sck\s
*=\s
*\'([^
\']+)\'', webpage, 'key
-pair
-id')
79 'Signature
': signature,
80 'Key
-Pair
-Id
': key_pair_id,
83 def _extract_http_video(self, webpage):
84 http_video_url = self._search_regex(r'P\
.s\s
*=\s
*\'([^
\']+)\'', webpage, 'video URL
')
85 http_video_url = update_url_query(http_video_url, self._extract_cf_auth(webpage))
87 'format_id
': 'http_video
',
88 'url
': http_video_url,
91 def _extract_http_audio(self, webpage, video_id):
92 fields = self._hidden_inputs(webpage)
93 http_audio_url = fields.get('filename
')
94 if not http_audio_url:
97 # base URL is found in the Location header in the response returned by
98 # GET https://www.infoq.com/mp3download.action?filename=... when logged in.
99 http_audio_url = compat_urlparse.urljoin('http
://res
.infoq
.com
/downloads
/mp3downloads
/', http_audio_url)
100 http_audio_url = update_url_query(http_audio_url, self._extract_cf_auth(webpage))
102 # audio file seem to be missing some times even if there is a download link
103 # so probe URL to make sure
104 if not self._is_valid_url(http_audio_url, video_id):
108 'format_id
': 'http_audio
',
109 'url
': http_audio_url,
113 def _real_extract(self, url):
114 video_id = self._match_id(url)
115 webpage = self._download_webpage(url, video_id)
117 video_title = self._html_search_regex(r'<title
>(.*?
)</title
>', webpage, 'title
')
118 video_description = self._html_search_meta('description
', webpage, 'description
')
121 # for China videos, HTTP video URL exists but always fails with 403
122 formats = self._extract_bokecc_formats(webpage, video_id)
125 self._extract_rtmp_video(webpage) +
126 self._extract_http_video(webpage) +
127 self._extract_http_audio(webpage, video_id))
129 self._sort_formats(formats)
133 'title
': video_title,
134 'description
': video_description,