Created
May 11, 2013 10:12
-
-
Save YoukouTenhouin/5559498 to your computer and use it in GitHub Desktop.
前N头像抓取器
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python2.7 | |
import urllib2 | |
import httplib | |
import re | |
import sys | |
import PIL.Image | |
usernamere = re.compile('username="?(.*)"') | |
portraitre = re.compile(r"'portrait' : '?(.*)',") | |
users = [] | |
def GetUserImageByName(username): | |
while True: | |
try: | |
page = urllib2.urlopen('http://www.baidu.com/p/'+username) | |
pcont = page.read() | |
try: | |
imagename = portraitre.findall(pcont)[0] | |
except IndexError: | |
page = urllib2.urlopen('http://tieba.baidu.com/i/sys/jump?un='+username) | |
pcont = page.read() | |
imagename = portraitre.findall(pcont)[0] | |
return 'http://himg.bdimg.com/sys/portrait/item/%s'%imagename | |
except httplib.IncompleteRead: | |
continue | |
break | |
return 'http://tb.himg.baidu.com/sys/portrait/item/%s'%imagename | |
def GetArgValueByKey(key): | |
return sys.argv[sys.argv.index(key)+1] | |
def GetPageNumByRank(rank): | |
return int((rank-1)/20)+1 | |
if __name__ == '__main__': | |
tieba_name = GetArgValueByKey('tieba') | |
tieba_name = urllib2.quote(tieba_name.decode(sys.stdin.encoding).encode('gbk')) | |
try: | |
begin = int(GetArgValueByKey('from')) | |
except ValueError: | |
begin = 0 | |
end = int(GetArgValueByKey('to')) | |
page_begin = GetPageNumByRank(begin) | |
page_end = GetPageNumByRank(end) | |
for i in range(page_begin,page_end+1): | |
print ('Getting page %d'%(i)) | |
url = ('http://tieba.baidu.com/f/like/furank?kw=%s&pn=%d'%(tieba_name,i)) | |
print 'URL:' + url | |
page = urllib2.urlopen(url).read() | |
users+=usernamere.findall(page) | |
try: | |
count = int(GetArgValueByKey('countbegin')) | |
except ValueError: | |
count = 1 | |
users = users[(begin%20)-1:end] | |
for user in users: | |
print ('%s -> %d.jpg'%(urllib2.unquote(user).decode('gbk'),count)) | |
file = open(str(count) + '.jpg','w') | |
try: | |
file.write(urllib2.urlopen(GetUserImageByName(user)).read()) | |
except IndexError: | |
print 'IndexError,Create Blank Image' | |
blank = PIL.Image.new('RGB',(110,110),(0,0,0)) | |
blank.save(file,'jpeg') | |
finally: | |
file.close() | |
count+=1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment