crawl-bilibili/user/get_face.py

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
'''
@File    :   get_face.py
@Time    :   2019/05/16 05:44:10
@Author  :   Liuyuqi 
@Version :   1.0
@Contact :   liuyuqi.gov@msn.cn
@License :   (C)Copyright 2019
@Desc    :   抓取用户头像，User表中头像字段导出后下载即可。
'''

import urllib
import re
import os, sys
src = "C:/Users/liuyuqi/Desktop/crawl_bilibili"
os.chdir(src)
sys.path.append(src)

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.request.urlretrieve(line, path)    #下载到指定位置
        line = f.readline()
        print('succeed:' + str(i))

f.close()