2509165045/final-practice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

代码

Browse Source
This commit is contained in:
2509165045
2026-06-11 21:13:45 +08:00
parent ea50503e0f
commit f44ad14760
3 changed files with 81 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
期末/project-10-at-2026-06-11-21-12-ee4e8f5c.json Normal file
View File

File diff suppressed because one or more lines are too long

10
期末/爬豆瓣
View File

@@ -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)