chinadialy 部分文字抓取

import requests
from bs4 import BeautifulSoup
url = "http://www.chinadaily.com.cn"
html = requests.get(url).text
data = list()
soup = BeautifulSoup(html, "lxml")
news = soup.find_all("div",{"class":"item"})
for index,new in enumerate(news):
    content_url = "http:" + new.a["href"]
    data.append(content_url + "\n")
    print(content_url)
    content_html = requests.get(content_url).text
    content_soup = BeautifulSoup(content_html, "lxml")
    h = content_soup.find("h1") 
   
    #print(h.text)
    data.append(h.text + "\n")
    #print(data)
    contents = content_soup.find("div", {"id":"Content"})
    try:
        p = contents.find_all("p")  #str段落
        for content in p:
            data.append(content.text + "\n")
        image_content =contents.find('figure',{"class":"image"})
        
        for figcontent in image_content.find("figcaption"):     #图片中的str
            data.append(figcontent.text + '\n')
    except:   #出更异常跳过
        pass
   
       
    
       
print(data)
with open("chinadialy.txt","w",encoding = "utf-8") as f:
    f.write("".join(data))