微博爬虫，python微博用户主页小姐姐图片内容采集爬虫

type: uid
value: 5118612601
containerid: 1005055118612601

import logging
logging.captureWarnings(True)

# 屏蔽warning信息
requests.packages.urllib3.disable_warnings()

html=requests.get(self.url,headers=self.headers,params=params,timeout=5,verify=False).content.decode('utf-8')

    def get_containerid(self):
        url = f'https://m.weibo.cn/api/container/getIndex?type=uid&value={self.uid}'
        data = requests.get(url,headers=self.headers,timeout=5,verify=False).content.decode('utf-8')
        content = json.loads(data).get('data')
        for data in content.get('tabsInfo').get('tabs'):
            if (data.get('tab_type') == 'weibo'):
                containerid = data.get('containerid')

        self.containerid=containerid

    def get_content(self,i):
        params={
            'type': 'uid',
            'value': self.uid,
            'containerid': self.containerid,
            'page':i,
        }
        html=requests.get(self.url,headers=self.headers,params=params,timeout=5,verify=False).content.decode('utf-8')
        data=json.loads(html)['data']
        cards=data['cards']
        #print(cards)
        j = 1
        for card in cards:
            if "mblog" in str(card):
                mblog = card['mblog']
                raw_text = mblog['raw_text']  # 文本内容
                print(raw_text)
                scheme=card['scheme'] #微博链接
                attitudes_count = mblog.get('attitudes_count') #点赞数
                comments_count = mblog.get('comments_count') #评论数
                created_at = mblog.get('created_at') #发布时间
                reposts_count = mblog.get('reposts_count') #转发数
                print(scheme)
                img_path=f'{self.path}{i}/{j}'
                os.makedirs(f'{img_path}/',exist_ok=True)
                with open(f'{img_path}/{j}.txt', 'a', encoding='utf-8') as f:
                    f.write(f'{raw_text}')

                img_urls=[]
                if mblog.get('pics') != None:
                    img_datas=mblog['pics']
                    for img_data in img_datas:
                        img_url=img_data['large']['url']
                        img_urls.append(img_url)
                    print(img_urls)

                    #多线程下载图片
                    self.get_imgs(img_urls,img_path)

                    #多进程下载图片
                    #self.get_pimgs(img_urls)

                with open(f'{self.uid}/{self.uid}.txt', 'a', encoding='utf-8') as fh:
                    fh.write("----第" + str(i) + "页，第" + str(j) + "条微博----" + "\n")
                    fh.write(f"微博地址： {str(scheme)}\n微博内容：{raw_text}\n"
                             f"发布时间：{str(created_at)}\n转发数：{str(reposts_count)}\n"
                             f"点赞数：{str(attitudes_count)}\n评论数：{str(comments_count)}\n\n")
                j=j+1

                time.sleep(2)

    #多线程下载图片
    def get_imgs(self,img_urls,img_path):
        threadings = []
        for img_url in img_urls:
            t = threading.Thread(target=self.get_img, args=(img_url,img_path))
            threadings.append(t)
            t.start()

        for x in threadings:
            x.join()

        print("多线程下载图片完成")


    def get_img(self, img_url,img_path):
        img_name = img_url.split('/')[-1]
        print(f'>> 正在下载图片：{img_name} ..')
        r = requests.get(img_url, timeout=8, headers=self.headers,verify=False)
        with open(f'{img_path}/{img_name}', 'wb') as f:
            f.write(r.content)
        print(f'>> 图片：{img_name} 下载完成！')