月度归档： 2022年10月

import requests,csv
from bs4 import BeautifulSoup
def getHtml(url):
    # 数据采集
    h = {
        'User-Agent': 'Mozilla / 5.0(Windows NT 10.0;WOW64)'
    }
    response = requests.get(url,headers = h)
    html = response.text
    # print(html)
# getHtml('https://movie.douban.com/top250')
# 数据解析：正则，BeautifulSoup，Xpath
    soup = BeautifulSoup(html,'lxml')
    filmtitle = soup.select('div.hd > a > span:nth-child(1)')
    ct = soup.select('div.bd > p:nth-child(1)')
    score = soup.select('div.bd > div > span.rating_num')
    evalue = soup.select('div.bd > div > span:nth-child(4)')
    print(score)
    filmlist = []
    for t,c,s,e in zip(filmtitle,ct,score,evalue):
        title = t.text
        content = c.text
        filmscore = s.text
        num = e.text.strip('人评价')
        director = content.strip().split()[1]
        if "主演:" in content:
            actor = content.strip().split('主演:')[1].split()[0]
        else:
            actor = None
        year = content.strip().split('/')[-3].split()[-1]
        area = content.strip().split('/')[-2].strip()
        filmtype = content.strip().split('/')[-1].strip()
        # print(num)
        listdata = [title,director,actor,year,area,filmtype,filmscore,num]
        filmlist.append(listdata)
    print(filmlist)
        # 存储数据
    with open('douban250.csv','a',encoding='utf-8',newline='') as f:
        w = csv.writer(f)
        w.writerows(filmlist)
 
# 函数调用
listtitle = ['title','director','actor','year','area','type','score','evalueate']
with open('douban250.csv','a',encoding='utf-8',newline='') as f:
    w = csv.writer(f)
    w.writerow(listtitle)
 
for i in range(0,226,25):
    getHtml('https://movie.douban.com/top250?start=%s&filter='%(i))
    # getHtml('https://movie.douban.com/top250?start=150&filter=')