forked from cvandeplas/pystemon
-
Notifications
You must be signed in to change notification settings - Fork 16
/
pystemon.yaml
145 lines (126 loc) · 5.7 KB
/
pystemon.yaml
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
#network: # Network settings
# ip: '1.1.1.1' # Specify source IP address if you want to bind on a specific one
archive:
save: yes # Keep
save-all: no # Keep a copy of all pasties
dir: "alerts" # Directory where matching pasties should be kept
dir-all: "archive" # Directory where all pasties should be kept (if save-all is set to yes)
compress: yes # Store the pasties compressed
db:
sqlite3: # Store information about the pastie in a database
enable: no # Activate this DB engine # NOT FULLY IMPLEMENTED
file: 'db.sqlite3' # The filename of the database
redis:
queue: no # Toggle PUSH to redis queue
server: "localhost"
port: 6379
database: 10
email:
alert: no # Enable/disable email alerts
from: [email protected]
server: 127.0.0.1 # Address of the server (hostname or IP)
port: 25 # Outgoing SMTP port: 25, 587, ...
username: '' # (optional) Username for authentication. Leave blank for no authentication.
password: '' # (optional) Password for authentication. Leave blank for no authentication.
subject: '[pystemon] - {subject}'
#####
# Definition of regular expressions to search for in the pasties
#
search:
# - description: '' # (optional) A human readable description. (used in alerting)
# search: '' # The regular expression to search for
# count: '' # (optional) How many hits should it have to be interesting?
# exclude: '' # (optional) Do not alert if this regular expression matches
# regex-flags: '' # (optional) Regular expression flags to give to the find function.
# # Default = re.IGNORECASE
# # Set to 0 to have no flags set
# # See http://docs.python.org/2/library/re.html#re.DEBUG for more info.
# # Warning: when setting this the default is overridden
# # example: 're.MULTILINE + re.DOTALL + re.IGNORECASE'
# to: '' # (optional) Additional recipients for email alert, comma separated list
- search: '[^a-zA-Z0-9]example\.com'
- search: '[^a-zA-Z0-9]foobar\.com'
- description: 'Download (non-porn)'
search: 'download'
exclude: 'porn|sex|teen'
count: 4
#####
# Configuration section for the paste sites
#
threads: 1 # number of download threads per site
site:
# example.com:
# archive-url: # the url where the list of last pasties is present
# # example: 'http://pastebin.com/archive'
# archive-regex: # a regular expression to extract the pastie-id from the page.
# # do not forget the () to extract the pastie-id
# # example: '<a href="/(\w{8})">.+</a></td>'
# download-url: # url for the raw pastie.
# # Should contain {id} on the place where the ID of the pastie needs to be placed
# # example: 'http://pastebin.com/raw.php?i={id}'
# update-max: 40 # every X seconds check for new updates to see if new pasties are available
# update-min: 30 # a random number will be chosen between these two numbers
# pastie-classname: # OPTIONAL: The name of a custom Class that inherits from Pastie
# # This is practical for sites that require custom fetchPastie() functions
pastebin.com:
enable: yes
archive-url: 'http://pastebin.com/archive'
archive-regex: '<a href="/(\w{8})">.+</a></td>'
download-url: 'http://pastebin.com/raw.php?i={id}'
update-max: 50
update-min: 40
# See https://pastebin.com/api_scraping_faq , you will need a pro account on pastebin
# You need to #whitelist you source IP and "Our scraping API is only available for LIFETIME PRO members, and only for those who have their IP whitelisted."
pastebin.com_pro:
enable: no
archive-url: 'https://scrape.pastebin.com/api_scraping.php?limit=500'
archive-regex: '"key": "(.+)",'
download-url: 'http://pastebin.com/api_scrape_item.php?i={id}'
update-max: 50
update-min: 40
slexy.org:
enable: yes
archive-url: 'http://slexy.org/recent'
archive-regex: '<a href="/view/([a-zA-Z0-9]+)">View paste</a>'
download-url: 'http://slexy.org/raw/{id}'
gist.github.com:
enable: no
archive-url: 'https://gist.github.com/gists'
archive-regex: '<span><a href="/([0-9]+)">gist'
download-url: 'https://raw.github.com/gist/{id}'
codepad.org:
enable: no
archive-url: 'http://codepad.org/recent'
archive-regex: '<a href="http://codepad.org/([a-zA-Z0-9]+)">view'
download-url: 'http://codepad.org/{id}/raw.txt'
safebin.net: # FIXME not finished
enable: no
archive-url: 'http://safebin.net/?archive'
archive-regex: '<a title="[a-zA-Z0-9 :,]+" href="/([0-9]+)">'
download-url: 'http://safebin.net/{id}'
update-max: 60
update-min: 50
# TODO
# http://www.safebin.net/ # more complex site
# http://www.heypasteit.com/ # http://www.heypasteit.com/clip/0IZA => incremental
# http://hastebin.com/ # no list of last pastes
# http://sebsauvage.net/paste/ # no list of last pastes
# http://tny.cz/ # no list of last pastes
# https://pastee.org/ # no list of last pastes
# http://paste2.org/ # no list of last pastes
# http://0bin.net/ # no list of last pastes
# http://markable.in/ # no list of last pastes
#####
# Configuration section to configure proxies
# Currently only HTTP proxies are permitted
#
proxy:
random: no
file: 'proxies.txt'
#####
# Configuration section for User-Agents
#
user-agent:
random: no
file: 'user-agents.txt'