[Python知识库]python爬虫03 —爬取静态页面（爬取豆瓣电影top250若干页的电影名称及评分）

import requests
import bs4
import time
# 定义请求头
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) /'
                 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36'
}

# 定义获取页面和解析数据方法
def getinfo(url):

    response = requests.get(url,headers= headers)

    soup = bs4.BeautifulSoup(response.text, 'lxml')

    moives = []
    # 基于class选择器获取元素
    items = soup.select('div.hd > a > span:nth-child(1)')
    for item in items:
        name = item.string
        moives.append([name,0])
    # 基于find_all方法获取元素
    scors = soup.find_all(class_='rating_num')
    i = 0
    for item in scors:
        scor = float(item.string)
        moives[i][1] =scor
        i+=1

    print(moives)

# 循环获取若干页面的电影名称和评分并打印
for page in range(5):
    url = f'https://movie.douban.com/top250?start={page * 25}&filter='
    print(f'第{page+1}页数据如下：')
    getinfo(url)
    time.sleep(1)
print('打印完毕！')