基本信息

---

下载

   源码介绍

---

爬取如上图话题的信息

def get_huati_data(url, page): try:
        url = url '&page={}'.format(page)
        html = requests.get(url, headers=headers, timeout=10)
        soup = BeautifulSoup(html.content, "html.parser") page_numbers = soup.find('ul', class_="s-scroll").find_all('li')
        all_datas = soup.find_all('div', class_="card-wrap", attrs={'action-type': 'feed_list_item'}) for all_data in all_datas:
            mid = all_data['mid'] '\t'  p = all_data.find('p', attrs={'node-type': 'feed_list_content'})
            name = p['nick-name']
            txt = p.text.strip()
            href = all_data.find('a', attrs={'action-type': 'fl_unfold'}) if href == None:
                href = all_data.find('p', class_='from').find_all('a')[0]['href'] else:
                href = href['href']
            con_time = all_data.find('p', class_='from').find_all('a')[0].text.strip()
            card_act = all_data.find('div', class_="card-act")
            lis = card_act.find_all('li')
            zhuanfa = lis[1].text.strip().replace('转发', '')
            comment = lis[2].text.strip().replace('评论', '')
            click = lis[3].text.strip() if zhuanfa == '' or len(zhuanfa) == 0:
                zhuanfa = 0  if comment == '' or len(comment) == 0:
                comment = 0  if click == '' or len(click) == 0:
                click = 0  url1 = 'https:'  href
            save_huati_data.append(mid)
            save_huati_data.append(name)
            save_huati_data.append(txt)
            save_huati_data.append(con_time)
            save_huati_data.append(zhuanfa)
            save_huati_data.append(comment)
            save_huati_data.append(click)
            save_huati_data.append(url1)
            writer.writerow(save_huati_data) print(save_huati_data)
            save_huati_data.clear() # return save_huati_data  except Exception as e: print(e) print("第"  str(page) "页获取（话题-文章-mid-url-zan）失败")