代码

期末/爬豆瓣

@@ -2,9 +2,9 @@ import requests
 from bs4 import BeautifulSoup as bs
 import json
 headers = {'User-Agent':'Mozilla/5.0(Windows NT 10.0;Win64; x64) AppleWebKit/537.36(KHTML,like Gecko) Chrome/91.0.4472.124 Safari/537.36'}
-url="https://movie.douban.com/top250?start=0"
+url="https://movie.douban.com/top250?start=25"
 data=[]
-resp = requests.get(url, headers = headers) 
+resp = requests.get(url, headers = headers)
 resp.encoding='uft-8'
 soup= bs(resp.text,"html.parser")
 items= soup.find_all("div",class_="item")
@@ -15,11 +15,11 @@ for i in range(len(items)):
 
     actors=items[i].find("div",class_="bd").get_text().strip()
     try:
-        actors=actors.split("主演：")[1].split("\n")[0]
+        actors=actors.split("主演:")[1].split("\n")[0]
     except:
         actors="无"
     try:
-        quote=items[i].find("div",class_="bd").find("p",class_="quote").get_text().strip()
+        quote=items[i].find("div", class_="bd").find("p",class_="quote").get_text().strip()
     except:
         quote="无"
     data.append({
@@ -30,4 +30,4 @@ for i in range(len(items)):
 print(data)
 
 with open("movie.json","w",encoding="utf-8") as f:
-    json.dump(data,f,ensure_ascii=False,indent=4)
+    json.dump(data,f,ensure_ascii=False,indent=4)