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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (C) 2014 Rubén Rodríguez <ruben@gnu.org>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
#
# This package parses https://addons.mozilla.org and generates a database
# listing the addons that are under a valid license. addons.mozilla.org is
# itself licensed as "CC Attribution Share-Alike v3.0 or any later version."
# Note that screenshots get licensed under the same license as the program.
#
# To run, install mysql-server, python-mysqldb and python-beautifulsoup
#
import re
import sys
import urllib2
import BeautifulSoup
server="https://addons.mozilla.org"
parsepages=2 #Number of pages per category to parse
dbuser="root"
dbpass=""
validlicenses = ['http://www.gnu.org/licenses/gpl-3.0.html',
'http://www.gnu.org/licenses/gpl-2.0.html',
'http://www.gnu.org/licenses/lgpl-3.0.html',
'http://www.gnu.org/licenses/lgpl-2.1.html',
'http://www.opensource.org/licenses/bsd-license.php',
'http://www.opensource.org/licenses/mit-license.php',
'http://www.mozilla.org/MPL/MPL-1.1.html',
'http://www.mozilla.org/MPL/2.0/']
categories = ['alerts-updates', 'appearance', 'bookmarks', 'download-management', 'feeds-news-blogging', 'games-entertainment', 'language-support', 'photos-music-videos', 'privacy-security', 'search-tools', 'shopping', 'social-communication', 'tabs', 'web-development', 'other']
def normalink(string):
return re.sub('\?.*', '', string)
def parselist(url):
print "PARSING LIST: " + url
l = []
request = urllib2.Request(url)
response = urllib2.urlopen(request)
soup = BeautifulSoup.BeautifulSoup(response)
for infodiv in soup.findAll('div',{'class':'info'}):
for h3 in infodiv.findAll('h3'):
for link in h3.findAll('a'):
l.append(re.sub('\?.*', '', link['href']))
return l
def parsepage(url, category):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
soup = BeautifulSoup.BeautifulSoup(response)
try:
licenseli = soup.findAll('li',{'class':'source-license'})[0]
license = licenseli.findAll('a')[0]['href']
if license not in validlicenses:
if license[0] == "h":
print "INVALID LICENSE: " + license
return 0
except:
return 0
name = re.sub('/$','', normalink(url))
name = re.sub('.*/','', name)
prettyname = soup.findAll(attrs={"property":"og:title"})[0]['content']
description = soup.findAll(attrs={"property":"og:description"})[0]['content']
rating = soup.findAll(attrs={"itemprop":"ratingValue"})[0]['content']
popularity = soup.findAll(attrs={"itemprop":"interactionCount"})[0]['content']
popularity = re.sub('UserDownloads:', '', popularity)
htmldescription = soup.findAll('div',{'id':'addon-description'})[0]
icon = normalink(soup.findAll(attrs={"property":"og:image"})[0]['content'])
screenshots = []
try:
previewdiv = soup.findAll('ul',{'id':'preview'})[0]
for a in previewdiv.findAll('a'):
screenshots.append(normalink(a['href']))
except:
pass
version = soup.findAll('span',{'class':'version-number'})[0].text
addondiv = soup.findAll('div',{'id':'addon'})[0]
addonp = addondiv.findAll('p',{'class':'install-button'})[0]
button = addonp.findAll('a')[0]
downloadlink = server + normalink(button['href'])
try:
homelink = soup.findAll('a',{'class':'home'})[1]['href']
homelink = re.sub('.*//','http://',homelink)
except:
homelink = ""
try:
supportlink = soup.findAll('a',{'class':'support'})[0]['href']
supportlink = re.sub('.*//','http://',supportlink)
except:
supportlink = ""
htmldescription = unicode(htmldescription)
description = unicode(description)
prettyname = unicode(prettyname)
description = re.sub('\'', '\\\'', description)
htmldescription = re.sub('\'', '\\\'', htmldescription)
prettyname = re.sub('\'', '\\\'', prettyname)
screenshots = unicode(screenshots)
sql = u'INSERT INTO addons.addons (`name`, `prettyname`, `description`, `htmldescription`, `icon`, `screenshots`, `version`, `rating`, `popularity`, `downloadlink`, `homelink`, `supportlink`, `retrievedlink`, `license`, `category`) VALUES ("' +name+ '", \'' +prettyname+ '\', \'' +description+ '\', \'' +htmldescription+ '\', "' +icon+ '", "' +screenshots+ '", "' +version+ '", "' +rating+ '", "' +popularity+ '", "' +downloadlink+ '", "' +homelink+ '", "' +supportlink+ '", "' +url+ '" , "' +license+ '", "' +category+ '");'
try:
cursor = db.cursor()
cursor.execute(sql)
cursor.close()
db.commit()
except:
print 'Failed to insert "' + name + '", query: "' + sql
else:
print "Added " + name + " " + url
import MySQLdb
db = MySQLdb.connect(host="localhost",user=dbuser,passwd=dbpass, charset="utf8", use_unicode=True)
cursor = db.cursor()
sql = """DROP DATABASE IF EXISTS addons;
CREATE DATABASE addons CHARACTER SET utf8 COLLATE utf8_general_ci;
USE addons;
CREATE TABLE addons(
id INT PRIMARY KEY AUTO_INCREMENT,
name VARCHAR(50),
prettyname VARCHAR(50),
description TEXT,
htmldescription TEXT,
icon VARCHAR(255),
screenshots TEXT,
version VARCHAR(20),
rating VARCHAR(10),
popularity INT,
downloadlink VARCHAR(255),
homelink VARCHAR(255),
supportlink VARCHAR(255),
retrievedlink VARCHAR(255),
license VARCHAR(255),
category VARCHAR(20)
);
"""
cursor.execute(sql)
cursor.close()
db.commit()
for category in categories:
links=[]
for page in range(1,1+parsepages):
links = links + parselist(server + "/en-US/firefox/extensions/" + category + "/?sort=popular&page="+str(page))
for link in links:
parsepage(server+link, category)
#tests
#parsepage("https://addons.mozilla.org/en-US/firefox/addon/twoo/", "test")
#parsepage("https://addons.mozilla.org/en-US/firefox/addon/what-about/", "test")
|