forked from calvinhobbes23/Skillshare-DL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
skillshare.py
203 lines (159 loc) · 7.58 KB
/
skillshare.py
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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
import requests, json, sys, re, os
import cloudscraper
from slugify import slugify
class Skillshare(object):
def __init__(
self,
cookie,
download_path=os.environ.get('FILE_PATH', './Skillshare'),
pk='BCpkADawqM2OOcM6njnM7hf9EaK6lIFlqiXB0iWjqGWUQjU7R8965xUvIQNqdQbnDTLz0IAO7E6Ir2rIbXJtFdzrGtitoee0n1XXRliD-RH9A-svuvNW9qgo3Bh34HEZjXjG4Nml4iyz3KqF',
brightcove_account_id=3695997568001,
):
self.cookie = cookie.strip().strip('"')
self.download_path = download_path
self.pk = pk.strip()
self.brightcove_account_id = brightcove_account_id
self.pythonversion = 3 if sys.version_info >= (3, 0) else 2
def is_unicode_string(self, string):
if (self.pythonversion == 3 and isinstance(string, str)) or (self.pythonversion == 2 and isinstance(string, str)):
return True
else:
return False
def download_course_by_url(self, url):
m = re.match(r'https://www.skillshare.com/classes/.*?/(\d+)', url)
if not m:
raise Exception('Failed to parse class ID from URL')
self.download_course_by_class_id(m.group(1))
def download_course_by_class_id(self, class_id):
data = self.fetch_course_data_by_class_id(class_id=class_id)
teacher_name = None
if 'vanity_username' in data['_embedded']['teacher']:
teacher_name = data['_embedded']['teacher']['vanity_username']
if not teacher_name:
teacher_name = data['_embedded']['teacher']['full_name']
if not teacher_name:
raise Exception('Failed to read teacher name from data')
if self.is_unicode_string(teacher_name):
teacher_name = teacher_name.encode('ascii', 'replace')
title = data['title']
if self.is_unicode_string(title):
title = title.encode('ascii', 'replace') # ignore any weird char
base_path = os.path.abspath(
os.path.join(
self.download_path,
slugify(teacher_name),
slugify(title),
)
).rstrip('/')
if not os.path.exists(base_path):
os.makedirs(base_path)
for s in data['_embedded']['sessions']['_embedded']['sessions']:
video_id = None
if 'video_hashed_id' in s and s['video_hashed_id']:
video_id = s['video_hashed_id'].split(':')[1]
if not video_id:
raise Exception('Failed to read video ID from data')
s_title = s['title']
if self.is_unicode_string(s_title):
s_title = s_title.encode('ascii', 'replace')
file_name = '{} - {}'.format(
str(s['index'] + 1).zfill(2),
slugify(s_title),
)
self.download_video(
fpath='{base_path}/{session}.mp4'.format(
base_path=base_path,
session=file_name,
),
video_id=video_id,
)
print('')
def fetch_course_data_by_class_id(self, class_id):
url = 'https://api.skillshare.com/classes/{}'.format(class_id)
scraper = cloudscraper.create_scraper(
browser={
'custom': 'Skillshare/4.1.1; Android 5.1.1',
},
delay=10
)
res = scraper.get(
url,
headers={
'Accept': 'application/vnd.skillshare.class+json;,version=0.8',
'User-Agent': 'Skillshare/5.3.0; Android 9.0.1',
'Host': 'api.skillshare.com',
'Referer': 'https://www.skillshare.com/',
'cookie': self.cookie,
}
)
if not res.status_code == 200:
raise Exception('Fetch error, code == {}'.format(res.status_code))
return res.json()
def download_video(self, fpath, video_id):
meta_url = 'https://edge.api.brightcove.com/playback/v1/accounts/{account_id}/videos/{video_id}'.format(
account_id=self.brightcove_account_id,
video_id=video_id,
)
scraper = cloudscraper.create_scraper(
browser={
'custom': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.3',
},
delay=10
)
meta_res = scraper.get(
meta_url,
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.3',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive',
'Accept': 'application/json;pk={}'.format(self.pk),
'Origin': 'https://www.skillshare.com'
}
)
if meta_res.status_code != 200:
raise Exception('Failed to fetch video meta')
if meta_res.json()['sources'][6]['container'] == 'MP4' and 'src' in meta_res.json()['sources'][6]:
dl_url = meta_res.json()['sources'][6]['src']
# break
else:
dl_url = meta_res.json()['sources'][1]['src']
print('Downloading {}...'.format(fpath))
if os.path.exists(fpath):
print('Video already downloaded, skipping...')
return
with open(fpath, 'wb') as f:
response = requests.get(dl_url, allow_redirects=True, stream=True)
total_length = response.headers.get('content-length')
if not total_length:
f.write(response.content)
else:
dl = 0
total_length = int(total_length)
for data in response.iter_content(chunk_size=4096):
dl += len(data)
f.write(data)
done = int(50 * dl / total_length)
sys.stdout.write("\r[%s%s]" % ('=' * done, ' ' * (50 - done)))
sys.stdout.flush()
print('')
def splash():
print(r"""
____ _ _ _ _ _ ____ _
/ ___|| | _(_) | |___| |__ __ _ _ __ ___ | _ \| |
\___ \| |/ / | | / __| '_ \ / _` | '__/ _ \_____| | | | |
___) | <| | | \__ \ | | | (_| | | | __/_____| |_| | |___
|____/|_|\_\_|_|_|___/_| |_|\__,_|_| \___| |____/|_____|
_ __ ___ _ _ _ _ _ ___ _ _
| / /| __>| \ || | | || . || | |
| \ | _> | || | | || |\ /
|_\_\|___>|_\_||__/_/ |_|_| |_|
####### # # ####### # # # ##### # #
# # ## # # # # # # # # # #
# # # # # # # # # # # # #
# # # # # ##### ####### # # # ###
# # # # # # # # ####### # # #
# # # ## # # # # # # # # #
####### # # ####### # # # # ##### # #
""")