Python简单爬虫

一、前期

1. 用开发者工具（F12）来找浏览器的代理
   
2. 引入模块
   bs4:数据获取，解析网页
   re：正则表达式，文字匹配
   urlib:URL，获取网页数据
   xlwt:进行Excel操作
3. 流程
   爬取网页->解析网页数据->保存数据

二、代码

爬取豆瓣电影top250详情，保存为表格。

import sys
from bs4 import BeautifulSoup
import re
import urllib
import xlwt

#全局变量，创建正则表达式对象，定义规则
findLink=re.compile(r'<a href="(.*?)">')
findImageSrc=re.compile(r'<img.*src="(.*?)"',re.S)
findTitle=re.compile(r'<span class="title">(.*)</span>')
findRating=re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
findJudge=re.compile(r'<span>(\d*)人评价</span>')
findInq=re.compile(r'<span class="inq">(.*)</span>')
findBd=re.compile(r'<p class="">(.*?)</p>',re.S)

def main():
    baseurl="https://movie.douban.com/top250?start="
    # 爬取网页
    datalist=getData(baseurl)
    savepath=".\\豆瓣电影Top250.xls"
    #保存数据
    savaData(datalist,savepath)
    #askURL("https://movie.douban.com/top250?start=")

#爬取网页
def getData(baseurl):
    datalist=[]
    #循环调用获取网页内容的函数10次
    for i in range(0,10):
        url=baseurl+str(i*25)
        html=askURL(url) #网页源码
        
        #解析数据
        soup=BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"): #查找符合要求的字符串，形成列表
            data=[]
            item=str(item)
            link=re.findall(findLink,item)[0]
            data.append(link)
            
            imgsrc=re.findall(findImgSrc,item)[0]
            data.append(imgsrc)
            
            titles=re.findall(findTitle,item) #片名可能有多个
            if len(titles)==2:
                ctitle=titles[0]
                data.append(ctitle)
                otitle=titles[1].replace("/"," ")
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')
            
            rating=re.findall(findRating,item)[0]
            data.append(rating)
            
            judgenum=re.findall(findJudge,item)[0]
            data.append(judgenum)
            
            inq=re.findall(findInq,item)
            if len(inq)!=0:
                inq=inq[0].replace("。"," ")
                data.append(inq)
            else:
                data.append(" ")
            
            bd=re.findall(findBd,item)[0]
            bd=re.sub('<br(\s+)?/>(\s+)?'," ",bd)
            bd=re.sub('/'," ",bd)
            data.append(bd.strip())
            
            datalist.append(data)
            
    return datalist
#得到一个url的指定网页内容
def askURL(url):
    #用户代理。模拟头部信息，将程序伪装成浏览器获取数据
    head={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36"}
    request=urllib.request.Request(url,headers=head)
    html=""
    try:
        response=urllib.request.urlopen(request)
        html=response.read().decode("utf-8")
    except:
        pass
    
 #保存数据
def saveData(datalist,savepath):
    print("saveing.... ")
    book=xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet=book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
    col=("电源链接","图片链接","影片名","别名","评分","评价人数","概况","相关信息")
    for i in range(0,8):
        sheet.write(0,i,col[i])
    for i in range(0,250):
        data=datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])
            
    book.save('豆瓣电影Top250.xls')