harry - 爬取图片

# 通过爬虫下载10张亚瑟图片
# 1.导包
import os
import requests
import re


# 电脑问我们想下载什么图片
# wenti = input("你想下载神魔图片")
wenti = "周杰伦"
number = 10
if not os.path.exists(wenti):
    os.makedirs(wenti)
# 3.构建网址
url = r'http://image.baidu.com/search/flip?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1497491098685_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&ctd=1497491098685%5E00_1519X735&word='
url = url + wenti
# print(url)
# 3.1获取源代码
get = requests.get(url)
# print(get.text)
# 3.2 正则表达式
tupian_url = re.findall(r'objURL":"(.*?)",', get.text)

a = 1
for i in tupian_url:
    print(i)
    p_type = i.split('.')[-1]
    # if len(p_type) > 5:
    #     p_type = 'jpg'
    print("正在下载第%d张" % a)
    a = a + 1
    tu_url = i
    try:
        tupian = requests.get(i,timeout=10)
        # open(文件名，访问模式) read读  write写
        name = "%s/%s_%d.%s" % (wenti, wenti, a, p_type)
        with open(name, 'wb') as f:
            f.write(tupian.content)
    except:
        print('第%d张图片下载失败！已跳过...'%a)

    if a >= number:
        break