python爬虫篇2：爬取百度图片

入门级

import requests
import re
import os
from urllib import error


def main():
    dirPath = "E:\python\yirenzhixia-images"
    word = "一人之下壁纸"
    url = "https://image.baidu.com/search/index?word=" + word + "&ie=utf-8&tn=baiduimage&pn="
    i = 1
    j = 0
    while i < 50:
        url = url + str(i)
        try:
            result = requests.get(url, timeout=10)
        except error.HTTPError as e:
            i += 1
            continue
        else:
            text = result.text
            list = re.findall('"thumbURL":"(.*?.jpg)"', text, re.S)
            if len(list) == 0:
                i += 1
                continue
            else:
                i += len(list)
                for enum in list:
                    print(enum)
                    try:
                        image = requests.get(enum, timeout=7)
                    except BaseException:
                        print("当前图片无法下载")
                        continue
                    else:
                        filePath = os.path.join(dirPath, "girl_image_" + str(j) + ".jpg")
                        f = open(filePath, 'wb')
                        f.write(image.content)
                        f.close()
                        j += 1


if __name__ == '__main__':
    main()

效果：