python爬取豆瓣影评示例

urllib:
Urllib库是python中的一个功能强大、用于操作URL，做爬虫时经常用

基本模块：
4个模块，主要针对URL(统一资源定位符)
request http的请求模块 ====爬虫
error 异常处理模块
parse 工具模块
robotparse 识别robots.txt

爬取豆瓣的地址：
https://movie.douban.com/subject/26322774/comments?start=30&limit=20&sort=new_score&status=P

#豆瓣反爬 模拟浏览器的信息
import urllib.request as request
import random
from bs4 import BeautifulSoup
import csv

#1.获取请求
def get_Request(url):
#     浏览器信息的设置  通过浏览器信息的模拟，实现随机浏览器信息的请求

#火狐浏览器
#User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0
#Host: movie.douban.com
    header1 = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0'
                ,'Host':'movie.douban.com'}
    # google
    header2 = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'
        , 'Host': 'movie.douban.com'}

    headList = [header1,header2]
    #随机产生一个
    randindex = random.randrange(0,len(headList))
    realHeader = headList[randindex]
    req = request.Request(url=url,headers=realHeader)
    return req


#2.通过请求获取数据
def getComment(url,commmentLists):
    req = get_Request(url)
    response = request.urlopen(req)
    print(response.getcode())

    soup = BeautifulSoup(response.read(),'html5lib')

    #soup

    comments = soup.select_one('#comments')
    commentItems = comments.select('.comment-item')
    for item in commentItems:
        comment = item.select_one('.comment')
        commentInfo = comment.select_one('.comment-info')
        #评论的用户
        author = commentInfo.select_one('a').text
        #打分  只有select找的的标签才是列表类型
        score = commentInfo.select('span')[1]['title']
        #获取短评
        commentText = comment.select_one('.short').text.replace('\n','')

       # print(author,score,commentText)
        #csv文件格式，逗号文件格式 excel 表格文件格式
        # 简单处理 下载成csv文件格式
        yingping = {'author':author,'score':score,'comment':commentText}
        commentLists.append(yingping)
    return commentLists





#3.下载评论
def downloadComment(commentLists):
    #语法 with as
    with open('逐梦.csv','w',newline='',encoding='utf-8') as file:
        csvwiter = csv.writer(file)
        for item in commentLists:
            #按每一行写入
            csvwiter.writerow([item['author'],item['score'],item['comment']])



#https://movie.douban.com/subject/26322774/comments?status=P

if __name__ == '__main__':
    #数据目标：短评   容器
    commentLists = []

    for index in range(0,10):
        url = 'https://movie.douban.com/subject/26322774/comments?start=%d&limit=20&sort=new_score&status=P'%(index*20)
        commentLists = getComment(url,commentLists)
    downloadComment(commentLists)