'''
豆瓣电影 top250 抓取电影信息,存到excel里面
使用requests爬取网页,使用bs4解析数据,使用pandas将数据存入Excel
目标网页:https://movie.douban.com/top250
仅供学习,不得用于违法用途
'''
import requests
from bs4 import BeautifulSoup
import pandas as pd
hearders = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
}
url = "https://movie.douban.com/top250"
def crawl_html(url):
'''
解析请求,爬取网页
:param url:请求地址
:return:返回的网页源码
'''
response = requests.get(url=url, headers=hearders)
return response.text
# print(crawl_html(url))
def parse_html(html):
"""
解析网页源码
:param html:页面源码
:return:页面 电影信息列表 []
"""
# 实例化soup
soup = BeautifulSoup(html, "lxml")
# 获取所有电影列表
movie_list = soup.select("ol.grid_view li")
# print(movie_list)
# 电影数据对象列表
movie_data_list = []
for movie in movie_list:
try:
rank = movie.select_one("div.pic em").text # 获取排名
title = movie.select_one("div.info span.title").text # 获取电影名称
info = movie.select_one("div.bd p").text.strip() # 获取电影描述信息
rating_num = movie.select_one("div.star span.rating_num").text # 获取评分
comment_count = movie.select("div.star span")[3].text.replace("人评价", "") # 获取电影评价人数
quote = movie.select_one("p.quote span.inq").text # 获取电影描述
movie_data_list.append({
"rank": rank,
"title": title,
"info": info,
"rating_num": rating_num,
"comment_count": comment_count,
"quote": quote
})
except:
continue
return movie_data_list
def export_excel(datas):
'''
导出数据到excel
:param datas: 数据
:return:
'''
df = pd.DataFrame(datas)
df.to_excel("豆瓣电影TOP250.xlsx")
# 执行爬取操作
export_excel(parse_html(crawl_html(url)))
以上代码是学习小峰博主视频编写