python爬虫（爬取图片）

第一步

载入爬虫模块

from requests_html import HTMLSession            #载入爬虫模块

第二步

创建session对象

from requests_html import HTMLSession            #载入爬虫模块
session =HTMLSession() #创建完毕

第三步

获得发现百度图片搜索规律并发起请求并匹配到图片的url

http://image.baidu.com/search/index?tn=baiduimage&fm=result&ie=utf-8&word=我们搜图片的关键字

from requests_html import HTMLSession            #载入爬虫模块
session =HTMLSession() #创建完毕
#拿二傻子为例
headers ={
    \'Accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9\',
    \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36\'
}
response = session.get(\'http://image.baidu.com/search/index?tn=baiduimage&fm=result&ie=utf-8&word=二傻子\',headers=headers)
#获取我们图片的url的正则匹配格式
img_url_regex = \'"thumbURL":"{}",\'
#解析并获取图片url_list
img_url_list = response.html.search_all(img_url_regex)

第四步

访问图片url并且保存下来

from requests_html import HTMLSession            #载入爬虫模块
session =HTMLSession() #创建完毕
#拿二傻子为例
headers ={
    \'Accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9\',
    \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36\'
}
response = session.get(\'http://image.baidu.com/search/index?tn=baiduimage&fm=result&ie=utf-8&word=二傻子\',headers=headers)
#获取我们图片的url的正则匹配格式
print(response.status_code)
img_url_regex = \'"thumbURL":"{}",\'
#解析并获取图片url_list
img_url_list = response.html.search_all(img_url_regex)
print(img_url_list)
mun=0
for url in img_url_list:
    mun+=1
    #访问图片链接
    response= session.get(url[0])
    #保存二进制并保存至本地
    with open(f\'第{mun}张.jpg\',\'wb\') as fw:
        fw.write(response.content)

第五步

类的封装

from requests_html import HTMLSession


class BaiDuImg:
    session = HTMLSession()
    img_url_regex = \'"thumbURL":"{}",\'
    url = \'\'
    img_url_list = []
    headers = {
        \'Accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9\',
        \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36\'
    }

    def get_search(self):
        search = input(\'请输入你要搜索的图片\')
        self.url = f\'http://image.baidu.com/search/index?tn=baiduimage&fm=result&ie=utf-8&word={search}\'

    def get_img_url_list(self):
        response = self.session.get(self.url,headers =self.headers)
        self.img_url_list = response.html.search_all(self.img_url_regex)

    def save_img(self):
        mun = 0
        for url in self.img_url_list:
            mun += 1
            # 访问图片链接
            response = self.session.get(url[0])
            # 保存二进制并保存至本地
            with open(f\'第{mun}张.jpg\', \'wb\') as fw:
                fw.write(response.content)

    def run(self):
        self.get_search()
        self.get_img_url_list()
        self.save_img()


if __name__ == \'__main__\':
    baidu = BaiDuImg()
    baidu.run()

后来有个研一的小姐姐说要把全部爬完那就改改

from requests_html import HTMLSession

class BaiDuImg:
    session = HTMLSession()
    img_url_regex = \'"thumbURL":"{}",\'
    url = \'\'
    img_url_list = []

    def get_search(self):
        search = input(\'请输入你要搜索的图片\')
        #有点点偷懒参数没有好好分析全,只对关键参数处理
        self.url = f\'https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord={search}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&hd=&latest=&copyright=&word={search}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&rn=30&gsm=\'
	
    def get_img_url_list(self):
        \'&pn=30000\'
        pn = 0
        try:
            while True:  #由于百度限制只能抓取450张,嗯可能能获取480张,我懒没接着分析了,如果真的需要私聊我我可以写全
                res = self.session.get(f\'{self.url}&pn={pn}\')
                print(res.json()[\'bdIsClustered\'])
                if  res.json()[\'bdIsClustered\']==\'2\':
                    break
                else:
                    pn+=30
                    for dic in res.json()[\'data\']:
                        img_url = dic.get(\'thumbURL\')
                        if img_url:
                            self.img_url_list.append(img_url)
        except Exception as e:
            pass



    def save_img(self):
        mun = 0
        for url in self.img_url_list:
            mun += 1
            # 访问图片链接
            response = self.session.get(url)
            # 保存二进制并保存至本地
            with open(f\'第{mun}张.jpg\', \'wb\') as fw:
                fw.write(response.content)
                print(f\'第{mun}张保存本地完毕\')

    def run(self):
        self.get_search()
        self.get_img_url_list()
        print(len(self.img_url_list))
        self.save_img()


if __name__ == \'__main__\':
    baidu = BaiDuImg()
    baidu.run()