python 爬虫爬取豆瓣top250保存到excel

最新推荐文章于 2025-09-29 11:14:24 发布

原创

最新推荐文章于 2025-09-29 11:14:24 发布 · 537 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#python

import requests
from bs4 import BeautifulSoup
import re
import xlwt
def getContent(row): #从第几条开始
    headers1 = {'User-Agent': 'Mozilla/4.0', 'content-type': 'text/html; charset=utf-8'}
    r = requests.get("https://movie.douban.com/top250?start="+str(row)+"&filter=",headers=headers1)
    html = r.text
    soup = BeautifulSoup(html, "html.parser")
    #print(html)
    return soup
films=[] #用这个做添加
#getContent(0)
def getItem(row):
    soup = getContent(row)
    grid_view=soup.find("ol",attrs={"class":"grid_view"})
    #print(grid_view) #输出所有的ol
    #访问 grid_view 的li
    items = grid_view.find_all("li")        #所有的li
    #print(items[0])                          #输出一个li 肖申克的救赎


    for li in items:
        film = []
        #print(li.find("span",attrs={"class":"title"}).text)     #输出所有标题
        title = li.find("span",attrs={"class":"title"}).getText()
        # print(title)
        # 添加电影标题
        film.append(title)
        rating_num = li.fin