教你用BeautifulSoup实现数据解析，并爬取豆瓣TOP250电影榜

5分钟使用Python爬取豆瓣TOP250电影榜

本视频的演示步骤：

1. 使用requests爬取网页
2. 使用BeautifulSoup实现数据解析
3. 借助pandas将数据写出到Excel

这三个库的详细用法，请看我的其他视频课程

import requests
from bs4 import BeautifulSoup
import pandas as pd
`
# 1、下载共10个页面的HTML

# 构造分页数字列表
page_indexs = range(0, 250, 25)
[*range(0, 250, 25)]
list(range(0, 250, 25) )

def download_all_htmls():
    """
    下载所有列表页面的HTML，用于后续的分析
    """
    htmls = []
    for idx in page_indexs:
        url = f"https://movie.douban.com/top250?start={idx}&filter="
        print("craw html:", url)
        r = requests.get(url,headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)"})
        
        if r.status_code != 200:
            raise Exception("error")
            
        htmls.append(r.text)
    return htmls

htmls = download_all_htmls()

craw html: https://movie.douban.com/top250?start=0&filter=
craw html: https://movie.douban.com/top250?start=25&filter=
craw html: https://movie.douban.com/top250?start=50&filter=
craw html: https://movie.douban.com/top250?start=75&filter=
craw html: https://movie.douban.com/top250?start=100&filter=
craw html: https://movie.douban.com/top250?start=125&filter=
craw html: https://movie.douban.com/top250?start=150&filter=
craw html: https://movie.douban.com/top250?start=175&filter=
craw html: https://movie.douban.com/top250?start=200&filter=
craw html: https://movie.douban.com/top250?start=225&filter=

# 2、解析HTML得到数据
def parse_single_html(html):
    """
    解析单个HTML，得到数据
    @return list({"link", "title", [label]})
    """
    soup = BeautifulSoup(html, 'html.parser')
    article_items = (
        soup.find("div", class_="article")
            .find("ol", class_="grid_view")
            .find_all("div", class_="item")
    )
    datas = []
    for article_item in article_items:
        rank = article_item.find("div", class_="pic").find("em").get_text()
        info = article_item.find("div", class_="info")
        title = info.find("div", class_="hd").find("span", class_="title").get_text()
        stars = (
            info.find("div", class_="bd")
                .find("div", class_="star")
                .find_all("span")
        )
        rating_star = stars[0]["class"][0]
        rating_num = stars[1].get_text()
        comments = stars[3].get_text()
        
        datas.append({
            "rank":rank,
            "title":title,
            "rating_star":rating_star.replace("rating","").replace("-t",""),
            "rating_num":rating_num,
            "comments":comments.replace("人评价", "")
        })
    return datas

# 查看第一个网页前5条记录
parse_single_html(htmls[0])[:5]

# 3. 执行所有的HTML页面的解析
all_datas = []
for html in htmls:
    '''
      extend() 函数用于在列表末尾一次性追加另一个序列中的多个值
      该方法没有返回值，但会在已存在的列表中添加新的列表内容
    '''
    all_datas.extend(parse_single_html(html))
``
all_datas
len(all_datas)

# 4. 将结果存入excel
df = pd.DataFrame(all_datas)
df.to_excel("豆瓣电影TOP250.xlsx")

extend方法：

aList = [123, ‘xyz’, ‘zara’, ‘abc’, 123];
bList = [2009, ‘manni’,2009];
aList.extend(bList)
aList

封装版：

import os

import json
import time
import pprint
import requests
import numpy as np
import pandas as pd
from bs4 import BeautifulSoup
from sqlalchemy import create_engine


def parse_single_url(html):

    '''html：一个url产生25条记录'''
    soup = BeautifulSoup(html,'html.parser')

    items = (
    soup.find('div',class_ = 'article')
        .find('ol',class_ = 'grid_view')
        .find_all('div',class_ = 'item')
    )
    

    '''需放在循环之外'''
    data1 = [] 

    for item in items:

        '''提取需要的字段'''
        rank1 = item.find('div',class_ = 'pic').find('em').get_text()
        info1 = item.find('div',class_= 'info')
        url1 = info1.find('div',class_ = 'hd').find('a').get('href')
        title1 = info1.find('div',class_ = 'hd').find('span',class_ = 'title').get_text()

        stars1 = (
        info1.find('div',class_ = 'bd')
            .find('div',class_ = 'star')
            .find_all('span')    
        )
        rating_star1 = stars1[0].get('class')[0] # 提取class属性值
        rating_num1 = stars1[1].get_text()
        comments1 = stars1[3].get_text()
        
        If_None = info1.find('div',class_ = 'bd').find('p',class_ = 'quote')
        
        '''if...else：解决AttributeError: 'NoneType' object has no attribute 'find'的报错问题 '''
        if If_None != None:
            quote1 = If_None.find('span',class_ = 'inq').get_text() # 提取文本
        else:
            quote1 = '缺失'
            
        '''
          将每条记录以字典形式存储，并追加到空列表中
          data1 = [] ,放在循环内部，每一遍都会被初始化
          print(tuple([rank1,title1,rating_star1,rating_num1,quote1,comments1,url1]))
          
        '''
        
        '''打印明细，便于定位问题：'''
        # print(tuple([rank1,title1,rating_star1,rating_num1,quote1,comments1,url1]))
        
        data1.append({
            'rank': int(rank1),
            'title':title1,
            'rating_star':int(rating_star1.replace('rating','').replace('-t','')),
            'rating_num':np.float(rating_num1),
            'quote':quote1.replace('。',''),
            'comment':int(comments1.replace('人评价','')),
            'url':url1   
        })
        
    '''缩进须对齐'''    
    return data1

# parse_single_url(html)

def download_all_htmls():
    htmls = []
    for idx in list(range(0,250,25)):
        url = f'https://movie.douban.com/top250?start={idx}&filter='
#         print('craw_url:',url)
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'}
        r = requests.get(url,headers = headers)
        if r.status_code != 200:
            raise Exception('error')
        '''将html文本内容追加存储在列表中'''
        htmls.append(r.text)
    return htmls

def data_to_Mysql(data,db_tname):
    
    engine = create_engine(f'mysql://xxx:[email protected]:3306/class201911?charset=utf8')
    Records = data.to_sql(db_tname, engine, index=False, if_exists='replace')
    
    print(f'{db_tname}数据入库成功，共计导入数据{Records}条')
    

if __name__ == '__main__':
    htmls = download_all_htmls()
    
    all_data = []
    for html in htmls:
        all_data.extend(parse_single_url(html))
        time.sleep(0.5)
    df = pd.DataFrame(all_data)
    
    '''存储数据到desktop'''
    os.chdir(r'C:\Users\DELL\Desktop')
#     df.to_excel('./top250.xlsx',index=False)
    
#      '''存储到数据库'''
#     data_to_Mysql(df,'movie_top_250')