爬虫

爬虫

全网爬取,能爬到1000多张

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
import requests

def save_pic(img_filename, img_data, n):
    with open(img_filename, 'wb') as f:  # write,read，wb是写入二进制
        f.write(img_data)
        print('第%s张保存完毕' % (n))

def main():

    for n in range(45):
        url = f'http://www.xiaohuar.com/list-1-%s.html' % (n + 1)
        print(url)
        response = requests.get(url)
        response.encoding = "gb2312"
        data = response.text
        # 拿到校花网所有的图片链接
        results = re.findall(r'" src="(.*?)" /></a>', data)
        name = re.findall(r'"  alt="(.*?)" src="', data)
        for n in range(len(name)):  # type:str
            try:
                # 判断是不是有链接的
                if results[n].startswith('http') and results[n].endswith("jpg"):
                    img_result = results[n]
                    # 获取图片内容
                    img_response = requests.get(img_result)
                    img_data = img_response.content
                    img_name = name[n] + ".jpg"
                    img_filename = r'd:\444\' + img_name
                    print("条件1")
                    # 保存图片内容
                    save_pic(img_filename, img_data, n)
                elif results[n].endswith("jpg"):
                    print(results[n])
                    img_result = 'http://www.xiaohuar.com/' + results[n]
                    # 获取图片内容
                    img_response = requests.get(img_result)
                    img_data = img_response.content
                    img_name = name[n]
                    img_filename = r'd:\55\' + img_name + '.jpg'
                    # 保存图片内容
                    save_pic(img_filename, img_data, n)
                else:
                    print('没有可以爬取的信息！')
            except:
                print('好像哪里出现了异常！')

        else:
            print('没有可以爬取的信息！')

if __name__ == '__main__':
    input('按任意键继续')
    main()