-
-
Notifications
You must be signed in to change notification settings - Fork 6
/
daemon_get_hashtag.py
297 lines (287 loc) · 11.7 KB
/
daemon_get_hashtag.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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
__filename__ = "daemon_get_hashtag.py"
__author__ = "Bob Mottram"
__license__ = "AGPL3+"
__version__ = "1.6.0"
__maintainer__ = "Bob Mottram"
__email__ = "bob@libreserver.org"
__status__ = "Production"
__module_group__ = "Daemon GET"
import json
import urllib.parse
from session import establish_session
from httpcodes import http_400
from httpcodes import http_404
from httpcodes import write2
from httpheaders import login_headers
from httpheaders import redirect_headers
from httpheaders import set_headers
from blocking import is_blocked_hashtag
from utils import convert_domains
from utils import get_nickname_from_actor
from fitnessFunctions import fitness_performance
from webapp_utils import html_hashtag_blocked
from webapp_search import html_hashtag_search
from webapp_search import hashtag_search_rss
from webapp_search import hashtag_search_json
from webapp_hashtagswarm import get_hashtag_categories_feed
def hashtag_search_rss2(self, calling_domain: str,
path: str, cookie: str,
base_dir: str, http_prefix: str,
domain: str, domain_full: str, port: int,
onion_domain: str, i2p_domain: str,
getreq_start_time,
system_language: str,
fitness: {}, debug: bool) -> None:
"""Return an RSS 2 feed for a hashtag
"""
hashtag = path.split('/tags/rss2/')[1]
if is_blocked_hashtag(base_dir, hashtag):
http_400(self)
return
nickname = None
if '/users/' in path:
actor = \
http_prefix + '://' + domain_full + path
nickname = \
get_nickname_from_actor(actor)
hashtag_str = \
hashtag_search_rss(nickname,
domain, port,
base_dir, hashtag,
http_prefix,
system_language)
if hashtag_str:
msg = hashtag_str.encode('utf-8')
msglen = len(msg)
set_headers(self, 'text/xml', msglen,
cookie, calling_domain, False)
write2(self, msg)
else:
origin_path_str = path.split('/tags/rss2/')[0]
origin_path_str_absolute = \
http_prefix + '://' + domain_full + origin_path_str
if calling_domain.endswith('.onion') and onion_domain:
origin_path_str_absolute = \
'http://' + onion_domain + origin_path_str
elif (calling_domain.endswith('.i2p') and onion_domain):
origin_path_str_absolute = \
'http://' + i2p_domain + origin_path_str
redirect_headers(self, origin_path_str_absolute + '/search',
cookie, calling_domain, 303)
fitness_performance(getreq_start_time, fitness,
'_GET', '_hashtag_search_rss2',
debug)
def hashtag_search_json2(self, calling_domain: str,
referer_domain: str,
path: str, cookie: str,
base_dir: str, http_prefix: str,
domain: str, domain_full: str, port: int,
onion_domain: str, i2p_domain: str,
getreq_start_time,
max_posts_in_feed: int,
fitness: {}, debug: bool) -> None:
"""Return a json collection for a hashtag
"""
page_number = 1
if '?page=' in path:
page_number_str = path.split('?page=')[1]
if page_number_str.isdigit():
page_number = int(page_number_str)
path = path.split('?page=')[0]
hashtag = path.split('/tags/')[1]
if is_blocked_hashtag(base_dir, hashtag):
http_400(self)
return
nickname = None
if '/users/' in path:
actor = \
http_prefix + '://' + domain_full + path
nickname = \
get_nickname_from_actor(actor)
hashtag_json = \
hashtag_search_json(nickname,
domain, port,
base_dir, hashtag,
page_number, max_posts_in_feed,
http_prefix)
if hashtag_json:
msg_str = json.dumps(hashtag_json)
msg_str = convert_domains(calling_domain, referer_domain,
msg_str, http_prefix, domain,
onion_domain, i2p_domain)
msg = msg_str.encode('utf-8')
msglen = len(msg)
set_headers(self, 'application/json', msglen,
None, calling_domain, True)
write2(self, msg)
else:
origin_path_str = path.split('/tags/')[0]
origin_path_str_absolute = \
http_prefix + '://' + domain_full + origin_path_str
if calling_domain.endswith('.onion') and onion_domain:
origin_path_str_absolute = \
'http://' + onion_domain + origin_path_str
elif (calling_domain.endswith('.i2p') and onion_domain):
origin_path_str_absolute = \
'http://' + i2p_domain + origin_path_str
redirect_headers(self, origin_path_str_absolute,
cookie, calling_domain, 303)
fitness_performance(getreq_start_time, fitness,
'_GET', '_hashtag_search_json',
debug)
def hashtag_search2(self, calling_domain: str,
path: str, cookie: str,
base_dir: str, http_prefix: str,
domain: str, domain_full: str, port: int,
onion_domain: str, i2p_domain: str,
getreq_start_time,
curr_session,
max_posts_in_hashtag_feed: int,
translate: {}, account_timezone: {},
bold_reading_nicknames: {},
fitness: {}, debug: bool,
recent_posts_cache: {},
max_recent_posts: int,
cached_webfingers: {},
person_cache: {},
project_version: str,
yt_replace_domain: str,
twitter_replacement_domain: str,
show_published_date_only: bool,
peertube_instances: [],
allow_local_network_access: bool,
theme_name: str,
system_language: str,
max_like_count: int,
signing_priv_key_pem: str,
cw_lists: {},
lists_enabled: {},
dogwhistles: {},
map_format: str,
access_keys: {},
min_images_for_accounts: [],
buy_sites: [],
auto_cw_cache: {},
ua_str: str,
mitm_servers: []) -> None:
"""Return the result of a hashtag search
"""
page_number = 1
if '?page=' in path:
page_number_str = path.split('?page=')[1]
if '#' in page_number_str:
page_number_str = page_number_str.split('#')[0]
if len(page_number_str) > 5:
page_number_str = "1"
if page_number_str.isdigit():
page_number = int(page_number_str)
hashtag = path.split('/tags/')[1]
if '?page=' in hashtag:
hashtag = hashtag.split('?page=')[0]
hashtag = urllib.parse.unquote_plus(hashtag)
if is_blocked_hashtag(base_dir, hashtag):
print('BLOCK: blocked hashtag #' + hashtag)
msg = html_hashtag_blocked(base_dir,
translate).encode('utf-8')
msglen = len(msg)
login_headers(self, 'text/html', msglen, calling_domain)
write2(self, msg)
return
nickname = None
if '/users/' in path:
nickname = path.split('/users/')[1]
if '/' in nickname:
nickname = nickname.split('/')[0]
if '?' in nickname:
nickname = nickname.split('?')[0]
timezone = None
if account_timezone.get(nickname):
timezone = account_timezone.get(nickname)
bold_reading = False
if bold_reading_nicknames.get(nickname):
bold_reading = True
hashtag_str = \
html_hashtag_search(nickname, domain, port,
recent_posts_cache,
max_recent_posts,
translate,
base_dir, hashtag, page_number,
max_posts_in_hashtag_feed,
curr_session,
cached_webfingers,
person_cache,
http_prefix,
project_version,
yt_replace_domain,
twitter_replacement_domain,
show_published_date_only,
peertube_instances,
allow_local_network_access,
theme_name,
system_language,
max_like_count,
signing_priv_key_pem,
cw_lists,
lists_enabled,
timezone, bold_reading,
dogwhistles,
map_format,
access_keys,
'search',
min_images_for_accounts,
buy_sites,
auto_cw_cache, ua_str,
mitm_servers)
if hashtag_str:
msg = hashtag_str.encode('utf-8')
msglen = len(msg)
set_headers(self, 'text/html', msglen,
cookie, calling_domain, False)
write2(self, msg)
else:
origin_path_str = path.split('/tags/')[0]
origin_path_str_absolute = \
http_prefix + '://' + domain_full + origin_path_str
if calling_domain.endswith('.onion') and onion_domain:
origin_path_str_absolute = \
'http://' + onion_domain + origin_path_str
elif (calling_domain.endswith('.i2p') and onion_domain):
origin_path_str_absolute = \
'http://' + i2p_domain + origin_path_str
redirect_headers(self, origin_path_str_absolute + '/search',
cookie, calling_domain, 303)
fitness_performance(getreq_start_time, fitness,
'_GET', '_hashtag_search', debug)
def get_hashtag_categories_feed2(self, calling_domain: str, path: str,
base_dir: str, proxy_type: str,
getreq_start_time,
debug: bool,
curr_session, fitness: {}) -> None:
"""Returns the hashtag categories feed
"""
curr_session = \
establish_session("get_hashtag_categories_feed",
curr_session, proxy_type,
self.server)
if not curr_session:
http_404(self, 27)
return
hashtag_categories = None
msg = \
get_hashtag_categories_feed(base_dir, hashtag_categories)
if msg:
msg = msg.encode('utf-8')
msglen = len(msg)
set_headers(self, 'text/xml', msglen,
None, calling_domain, True)
write2(self, msg)
if debug:
print('Sent rss2 categories feed: ' +
path + ' ' + calling_domain)
fitness_performance(getreq_start_time, fitness,
'_GET', '_get_hashtag_categories_feed', debug)
return
if debug:
print('Failed to get rss2 categories feed: ' +
path + ' ' + calling_domain)
http_404(self, 28)