1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
import re
from .common import InfoExtractor
from .vimeo import VimeoIE
from ..utils import (
ExtractorError,
int_or_none,
merge_dicts,
try_get,
unescapeHTML,
unified_timestamp,
urljoin,
)
class RayWenderlichIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
videos\.raywenderlich\.com/courses|
(?:www\.)?raywenderlich\.com
)/
(?P<course_id>[^/]+)/lessons/(?P<id>\d+)
'''
_TESTS = [{
'url': 'https://www.raywenderlich.com/3530-testing-in-ios/lessons/1',
'info_dict': {
'id': '248377018',
'ext': 'mp4',
'title': 'Introduction',
'description': 'md5:804d031b3efa9fcb49777d512d74f722',
'timestamp': 1513906277,
'upload_date': '20171222',
'duration': 133,
'uploader': 'Ray Wenderlich',
'uploader_id': 'user3304672',
},
'params': {
'noplaylist': True,
'skip_download': True,
},
'add_ie': [VimeoIE.ie_key()],
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
'only_matching': True,
}]
@staticmethod
def _extract_video_id(data, lesson_id):
if not data:
return
groups = try_get(data, lambda x: x['groups'], list) or []
if not groups:
return
for group in groups:
if not isinstance(group, dict):
continue
contents = try_get(data, lambda x: x['contents'], list) or []
for content in contents:
if not isinstance(content, dict):
continue
ordinal = int_or_none(content.get('ordinal'))
if ordinal != lesson_id:
continue
video_id = content.get('identifier')
if video_id:
return str(video_id)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
course_id, lesson_id = mobj.group('course_id', 'id')
display_id = f'{course_id}/{lesson_id}'
webpage = self._download_webpage(url, display_id)
thumbnail = self._og_search_thumbnail(
webpage, default=None) or self._html_search_meta(
'twitter:image', webpage, 'thumbnail')
if '>Subscribe to unlock' in webpage:
raise ExtractorError(
'This content is only available for subscribers',
expected=True)
info = {
'thumbnail': thumbnail,
}
vimeo_id = self._search_regex(
r'data-vimeo-id=["\'](\d+)', webpage, 'vimeo id', default=None)
if not vimeo_id:
data = self._parse_json(
self._search_regex(
r'data-collection=(["\'])(?P<data>{.+?})\1', webpage,
'data collection', default='{}', group='data'),
display_id, transform_source=unescapeHTML, fatal=False)
video_id = self._extract_video_id(
data, lesson_id) or self._search_regex(
r'/videos/(\d+)/', thumbnail, 'video id')
headers = {
'Referer': url,
'X-Requested-With': 'XMLHttpRequest',
}
csrf_token = self._html_search_meta(
'csrf-token', webpage, 'csrf token', default=None)
if csrf_token:
headers['X-CSRF-Token'] = csrf_token
video = self._download_json(
f'https://videos.raywenderlich.com/api/v1/videos/{video_id}.json',
display_id, headers=headers)['video']
vimeo_id = video['clips'][0]['provider_id']
info.update({
'_type': 'url_transparent',
'title': video.get('name'),
'description': video.get('description') or video.get(
'meta_description'),
'duration': int_or_none(video.get('duration')),
'timestamp': unified_timestamp(video.get('created_at')),
})
return merge_dicts(info, self.url_result(
VimeoIE._smuggle_referrer(
f'https://player.vimeo.com/video/{vimeo_id}', url),
ie=VimeoIE.ie_key(), video_id=vimeo_id))
class RayWenderlichCourseIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
videos\.raywenderlich\.com/courses|
(?:www\.)?raywenderlich\.com
)/
(?P<id>[^/]+)
'''
_TEST = {
'url': 'https://www.raywenderlich.com/3530-testing-in-ios',
'info_dict': {
'title': 'Testing in iOS',
'id': '3530-testing-in-ios',
},
'params': {
'noplaylist': False,
},
'playlist_count': 29,
}
@classmethod
def suitable(cls, url):
return False if RayWenderlichIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
course_id = self._match_id(url)
webpage = self._download_webpage(url, course_id)
entries = []
lesson_urls = set()
for lesson_url in re.findall(
rf'<a[^>]+\bhref=["\'](/{course_id}/lessons/\d+)', webpage):
if lesson_url in lesson_urls:
continue
lesson_urls.add(lesson_url)
entries.append(self.url_result(
urljoin(url, lesson_url), ie=RayWenderlichIE.ie_key()))
title = self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title', default=None)
return self.playlist_result(entries, course_id, title)
|
