-
Notifications
You must be signed in to change notification settings - Fork 21
/
patreon_importer.py
212 lines (194 loc) · 8.12 KB
/
patreon_importer.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
204
205
206
207
208
209
210
211
212
import cloudscraper
import psycopg2
import datetime
import config
import time
import uuid
import json
import sys
from psycopg2.extras import RealDictCursor
from urllib.parse import urlparse
from os.path import join, splitext
from download import download_file, DownloaderException
from gallery_dl import text
from flag_check import check_for_flags
from proxy import get_proxy
initial_api = 'https://www.patreon.com/api/stream' + '?include=' + ','.join([
'user',
'images',
'audio',
'attachments',
'user_defined_tags',
'campaign',
'poll.choices',
'poll.current_user_responses.user',
'poll.current_user_responses.choice',
'poll.current_user_responses.poll',
'access_rules.tier.null'
]) + '&fields[post]=' + ','.join([
'change_visibility_at',
'comment_count',
'content',
'current_user_can_delete',
'current_user_can_view',
'current_user_has_liked',
'embed',
'image',
'is_paid',
'like_count',
'min_cents_pledged_to_view',
'post_file',
'published_at',
'edited_at',
'patron_count',
'patreon_url',
'post_type',
'pledge_url',
'thumbnail_url',
'teaser_text',
'title',
'upgrade_url',
'url',
'was_posted_by_campaign_owner',
]) + '&fields[user]=' + ','.join([
'image_url',
'full_name',
'url'
]) + '&fields[campaign]=' + ','.join([
'avatar_photo_url',
'earnings_visibility',
'is_nsfw',
'is_monthly',
'name',
'url'
]) + '&json-api-use-default-includes=false' + '&json-api-version=1.0'
def import_posts(key, url = initial_api):
conn = psycopg2.connect(
host = config.database_host,
dbname = config.database_dbname,
user = config.database_user,
password = config.database_password,
cursor_factory = RealDictCursor
)
scraper = cloudscraper.create_scraper()
scraper_data = scraper.get(url, cookies = { 'session_id': key }, proxies=get_proxy()).json()
for post in scraper_data['data']:
try:
file_directory = f"files/{post['relationships']['user']['data']['id']}/{post['id']}"
attachments_directory = f"attachments/{post['relationships']['user']['data']['id']}/{post['id']}"
cursor1 = conn.cursor()
cursor1.execute("SELECT * FROM dnp WHERE id = %s AND service = 'patreon'", (post['relationships']['user']['data']['id'],))
bans = cursor1.fetchall()
if len(bans) > 0:
continue
check_for_flags(
'patreon',
post['relationships']['user']['data']['id'],
post['id']
)
cursor2 = conn.cursor()
cursor2.execute("SELECT * FROM booru_posts WHERE id = %s AND service = 'patreon'", (post['id'],))
existing_posts = cursor2.fetchall()
if len(existing_posts) > 0:
continue
post_model = {
'id': post['id'],
'"user"': post['relationships']['user']['data']['id'],
'service': 'patreon',
'title': post['attributes']['title'],
'content': '',
'embed': {},
'shared_file': False,
'added': datetime.datetime.now(),
'published': post['attributes']['published_at'],
'edited': post['attributes']['edited_at'],
'file': {},
'attachments': []
}
if post['attributes']['content']:
post_model['content'] = post['attributes']['content']
for image in text.extract_iter(post['attributes']['content'], '<img data-media-id="', '>'):
download_url = text.extract(image, 'src="', '"')[0]
path = urlparse(download_url).path
ext = splitext(path)[1]
fn = str(uuid.uuid4()) + ext
filename, _ = download_file(
join(config.download_path, 'inline'),
download_url,
name = fn
)
post_model['content'] = post_model['content'].replace(download_url, f"/inline/{filename}")
if post['attributes']['embed']:
post_model['embed']['subject'] = post['attributes']['embed']['subject']
post_model['embed']['description'] = post['attributes']['embed']['description']
post_model['embed']['url'] = post['attributes']['embed']['url']
if post['attributes']['post_file']:
filename, _ = download_file(
join(config.download_path, file_directory),
post['attributes']['post_file']['url'],
name = post['attributes']['post_file']['name']
)
post_model['file']['name'] = post['attributes']['post_file']['name']
post_model['file']['path'] = f'/{file_directory}/{filename}'
for attachment in post['relationships']['attachments']['data']:
filename, _ = download_file(
join(config.download_path, attachments_directory),
f"https://www.patreon.com/file?h={post['id']}&i={attachment['id']}",
cookies = { 'session_id': key }
)
post_model['attachments'].append({
'name': filename,
'path': f'/{attachments_directory}/{filename}'
})
if post['relationships']['images']['data']:
for image in post['relationships']['images']['data']:
for media in list(filter(lambda included: included['id'] == image['id'], scraper_data['included'])):
if media['attributes']['state'] != 'ready':
continue
filename, _ = download_file(
join(config.download_path, attachments_directory),
media['attributes']['download_url'],
name = media['attributes']['file_name']
)
post_model['attachments'].append({
'name': filename,
'path': f'/{attachments_directory}/{filename}'
})
if post['relationships']['audio']['data']:
for audio in post['relationships']['audio']['data']:
for media in list(filter(lambda included: included['id'] == audio['id'], scraper_data['included'])):
if media['attributes']['state'] != 'ready':
continue
filename, _ = download_file(
join(config.download_path, attachments_directory),
media['attributes']['download_url'],
name = media['attributes']['file_name']
)
post_model['attachments'].append({
'name': filename,
'path': f'/{attachments_directory}/{filename}'
})
post_model['embed'] = json.dumps(post_model['embed'])
post_model['file'] = json.dumps(post_model['file'])
for i in range(len(post_model['attachments'])):
post_model['attachments'][i] = json.dumps(post_model['attachments'][i])
columns = post_model.keys()
data = ['%s'] * len(post_model.values())
data[-1] = '%s::jsonb[]' # attachments
query = "INSERT INTO booru_posts ({fields}) VALUES ({values})".format(
fields = ','.join(columns),
values = ','.join(data)
)
cursor3 = conn.cursor()
cursor3.execute(query, list(post_model.values()))
conn.commit()
except DownloaderException:
continue
conn.close()
if scraper_data['links'].get('next'):
import_posts(key, 'https://' + scraper_data['links']['next'])
if __name__ == '__main__':
if len(sys.argv) > 1:
import_posts(sys.argv[1])
else:
print('Argument required - Login token')