├── README
└── fb_albums.py


/README:
--------------------------------------------------------------------------------
1 | 


--------------------------------------------------------------------------------
/fb_albums.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/python
 2 | 
 3 | __author__ = "Nicolas Seriot"
 4 | __date__ = "2010-09-26"
 5 | __license__ = "GPL"
 6 | 
 7 | """
 8 | Download photos from Facebook photo albums.
 9 | """
10 | 
11 | import re
12 | import urllib
13 | import urllib2
14 | import cookielib
15 | import optparse
16 | import getpass
17 | from optparse import OptionParser
18 | 
19 | # parse the command line
20 | parser = optparse.OptionParser("usage: %prog -e EMAIL -a ALBUM_URL [-p PASSWORD]")
21 | parser.add_option("-e", "--email", dest="email")
22 | parser.add_option("-p", "--password", dest="password")
23 | parser.add_option("-a", "--album_url", dest="album_url")
24 | 
25 | (options, args) = parser.parse_args()
26 | 
27 | if not options.email or not options.album_url:
28 |     parser.error("-- please fill all options")
29 |     exit(0)
30 | 
31 | password = options.password if options.password else getpass.getpass("Password: ")
32 | 
33 | # install an url opener with cookies
34 | cookie_jar = cookielib.LWPCookieJar()
35 | opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie_jar))
36 | urllib2.install_opener(opener)
37 | 
38 | print "-- getting facebook cookies"
39 | urllib2.urlopen('http://www.facebook.com/')
40 | 
41 | print "-- loggin in"
42 | query_args = { 'email':options.email, 'pass':password }
43 | encoded_args = urllib.urlencode(query_args)
44 | url = 'https://login.facebook.com/login.php'
45 | urllib2.urlopen(url, encoded_args)
46 | 
47 | print "-- reading album page " + url
48 | s = urllib2.urlopen(options.album_url).read()
49 | 
50 | pattern = "http://www.facebook.com/photo.php\?pid=\d+&id=\d+&ref=fbx_album"
51 | photo_page_urls = re.findall(pattern, s)
52 | photo_page_urls = map(lambda x:x.replace('&','&'), photo_page_urls)
53 | 
54 | print "-- found %d photos" % len(photo_page_urls)
55 | 
56 | photos_urls = []
57 | for url in photo_page_urls:
58 |     print "-- reading photo page " + url
59 |     s = urllib2.urlopen(url).read()
60 |     pattern = '<img src="(http://sphotos\.ak\.fbcdn.net/.*?\.jpg)" width="\d+" height="\d+" id="myphoto" />'
61 |     photo_url = re.findall(pattern, s)[0]
62 |     photos_urls.append(photo_url)
63 | 
64 | count = 0
65 | for url in photos_urls:
66 |     count += 1
67 |     print "-- downloading " + url
68 |     urllib.urlretrieve (url, "%d.jpg" % count)
69 | 
70 | print "-- finished"
71 | 


--------------------------------------------------------------------------------