python的requests库实现百度图片爬取

最新推荐文章于 2024-05-01 23:31:21 发布

lxj2116

最新推荐文章于 2024-05-01 23:31:21 发布

阅读量682

点赞数 1

文章标签： python 爬虫开发语言

本文链接：https://blog.csdn.net/lxj2116/article/details/125204193

版权

python的requests库实现百度图片爬取

主要功能：
通过用户输入的图片类型和数量进行图片的爬取并保存到本地。
结果展示：
代码展示：

# -*- coding:utf8 -*-
import random
import json
import requests
import os
import time
# 务必在init函数的header1中填入自己的百度账号cookie
class BaiduImageSpider(object):
    def __init__(self):
        self.url = 'https://image.baidu.com/search/acjson?'
        # 获取百度图片搜索页面时用于验证身份信息
        self.header1 = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36',
            'Cookie': '登录百度账号后通过F12在请求头中自己获取cookie',
            'Accept-Encoding': 'gzip, deflate, br',
            'Accept-Language': 'zh - CN, zh;q = 0.9, en;q = 0.8',
            'Accept': 'text/plain, */*; q=0.01'
        }

        # 下载图片时用于验证身份信息
        self.header2 = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'}

    # 获取图片
    def get_image(self, url, word, param):
        save_url = []
        html = requests.get(url=url, headers=self.header1, params=param).text
        jpg = json.loads(html)  # 类型：字典
        jpg["data"].pop()  # 类型：列表,去除列表中最后的一个空字典
        for i in jpg["data"]:
            save_url.append(i['thumbURL'])
        # 创建目录，用于保存图片
        directory = 'D:/Picture/image/{}/'.format(word)
        # 如果目录不存在则创建，此方法常用
        if not os.path.exists(directory):
            os.makedirs(directory)

        # 添加计数
        i = 1
        for img_link in save_url:
            filename = '{}{}_{}.jpg'.format(directory, word, i)
            self.save_image(img_link, filename)
            i += 1
        print("{}-下载完成！".format(word))

    # 下载图片
    def save_image(self, img_link, filename):
        html = requests.get(url=img_link, headers=self.header2).content
        with open(filename, 'wb') as f:
            f.write(html)
        print(filename, '下载成功')
        time.sleep(random.uniform(0, 1))

    # 入口函数
    def run(self):
        word = input("请输入您想要下载的图片类型？")
        num = input("请输入您想要下载的数量？")
        param = {
            "tn": "resultjson_com",
            "logid": "7594783827726186484",
            "ipn": "rj",
            "ct": "201326592",
            "fp": "result",
            "word": word,
            "queryWord": word,
            "cl": "2",
            "lm": "-1",
            "ie": "utf-8",
            "oe": "utf-8",
            "st": "-1",
            "z": "0",
            "ic": "0",
            "hd": "0",
            "latest": "0",
            "copyright": "0",
            "face": "0",
            "istype": "2",
            "nc": "1",
            "pn": "0",
            "rn": num,
            "gsm": "1e"
        }
        self.get_image(url=self.url, word=word, param=param)


if __name__ == '__main__':
    spider = BaiduImageSpider()
    spider.run()