crawl-bilibili/user/get_face.py

# -*-coding:utf8-*-

import urllib
import re

f = open("../data/bilibili_user_face.txt")
line = f.readline()
for i in range(1, 1000):
    print(line,)
    if re.match('http://static.*', line):
        line = f.readline()
        print('noface:' + str(i))
    else:
        path = r"../data/face/" + str(i) + ".jpg"
        data = urllib.urlretrieve(line, path)
        line = f.readline()
        print('succeed:' + str(i))

f.close()