python3爬取网页图片路径并写入文件

Posted 2021-02-17 尘世间迷茫的小书童

import re
import urllib.request

# 获取网页文件
def getHtml(url):
    response = urllib.request.urlopen(‘https://www.zhipin.com/?ka=header-home‘);
    return response.read();

# 写入数据到文件
def writeFile(fileName,data):
    # 打开文件方式为‘a‘可不覆盖原有数据
    htmlFile = open(fileName, ‘a‘);
    htmlFile.write(data);
    htmlFile.close();

# 截取后缀为.jpg的图片
def getImgSrc(fileName):
    # decode()将string转为byte
    imgUrl = re.findall(r‘https:.+.jpg‘,fileName.decode(‘utf-8‘));
    return imgUrl;

html = getHtml(‘https://www.imooc.com/‘);
print(html);

imgUrl = getImgSrc(html);
for i in imgUrl:
    print(i);
    writeFile(‘imgUrl.txt‘, i);