Python Google 图像搜索结果原图抓取

# !/usr/bin/python3
# -*- coding:utf-8 -*-
"""
@author: JHC000abc@gmail.com
@file: test.py
@time: 2023/11/6 20:45
@desc:

"""
from sdk.temp.temp_supports import IsSolution
from sdk.utils.util_network import NetWorkRequests
from PIL import Image


class Solution(IsSolution):
    def __init__(self, **kwargs):
        super(Solution, self).__init__()
        self.__dict__.update({k: v for k, v in [
            i for i in locals().values() if isinstance(i, dict)][0].items()})
        self.net = NetWorkRequests()
        self.headers = {
            "authority": "www.google.com",
            "accept-language": "zh-CN,zh;q=0.9",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
            }
        self.error_lis = []

    def get_query(self, in_path):
        with open(in_path, "r", encoding="utf-8")as fp:
            for i in fp:
                yield i.strip()

    def get_data(self, tag, query=None, url=None, headers=None):
        if query:
            url = "https://www.google.com/search?q={}&tbm=isch".format(query)
        # print("url",url)
        # proxies = {
        #     "http": "http://127.0.0.1:1080",
        #     "https": "http://127.0.0.1:1080",
        # }
        proxies = None
        res = self.net._requests(method="GET", url=url, headers=headers, proxies=proxies)
        if res["status"] == 0:
            return res["msg"]
        else:
            self.error_lis.append([tag])
            print("获取数据失败:{},请切换代理重试".format(tag))
            # raise ValueError("获取数据失败:{},请切换代理重试".format(url))
            return None

    def get_image_urls(self, url_lis):
        with open("temp.html", "r", encoding="utf-8")as fpr:
            data = fpr.read()
            for dat in data.split(","):
                dat = dat.split("?")[0].replace('"', "").replace("[", "")
                # print(dat)
                if (dat.startswith('https://') and dat.endswith('.jpg')) or (
                        dat.startswith('http://') and dat.endswith('.jpg')) or (
                        dat.startswith('https://') and dat.endswith('.png')):
                    print(dat)
                    url_lis.append(dat)
                    if len(url_lis) >= 3:
                        break

        return url_lis

    def download_images(self, url_list, query, save_path):
        for index, url in enumerate(url_list):
            print("开始下载:{}".format(url))
            response = self.get_data(url=url, tag=query, headers=self.headers)
            if response:
                content = response.content
                name = "{}_{}.jpg".format(query, index + 1)
                image_file = self.folder.merge_path([save_path, name])
                with open(image_file, "wb")as fp:
                    fp.write(content)

                if not self.is_image_corrupted(image_file):
                    print("图像损坏:{}".format(query))
                    self.error_lis.append([url])

                print("{} 下载完成:{}".format(name, url))

    def is_image_corrupted(self, file_path):
        try:
            img = Image.open(file_path)  # 尝试打开图像文件
            img.verify()  # 验证图像文件的完整性
            return True  # 图像文件未损坏
        except (IOError, SyntaxError):
            return False  # 图像文件损坏

    def process(self, **kwargs):
        """

        :param kwargs:
        :return:
        """
        in_path = kwargs["in_path"]
        save_path = kwargs["save_path"]
        self.folder.create_folder(save_path)
        for query in self.get_query(in_path):
            url_lis = []
            response = self.get_data(tag=query, query=query, headers=self.headers)
            if response:
                html_str = response.text
                # print(html_str)
                with open("temp.html", "w", encoding="utf-8")as fp:
                    fp.write(html_str)
            # url_lis = []
                url_lis = self.get_image_urls(url_lis)
                self.download_images(url_lis, query, save_path)

        if self.error_lis:
            self.save_result(self.folder.merge_path([save_path, "下载失败链接.txt"]), data=self.error_lis)


if __name__ == '__main__':
    in_path = R"D:\Desktop\1.txt"
    save_path = R"D:\Desktop\2"
    e = Solution()
    e.process(in_path=in_path, save_path=save_path)