LHL'Python 经典爬虫教程(豆瓣) 包含源代码 ，封装程序，图片 V1.0.0.3

LHL’Python 之 经典爬虫教程(豆瓣)

#-*-coding:utf-8-*-
##2020.5.8.14.01.00
##罗宏亮船新作品
##
from typing import Pattern
from bs4 import BeautifulSoup
import  re
import urllib
import xlwt
import urllib.request
import sqlite3


def main():
    baseurl="https://movie.douban.com/top250?start="
    datalist=getData(baseurl)
    savepath='罗宏亮船新爬虫之豆瓣电影TOP250.xls'
    saveData(savepath,datalist)

findLink=re.compile(r'<a href=(.*?)">')
#网址
findImgSrc=re.compile(r'<img.*src="(.*?)"',re.S)
#图片
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 getData(baseurl):
    datalist=[]
    for i in range(0,10):
        url=baseurl+str(i*25)
        html=askURL(url)
        soup=BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):
            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)
            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)
            judge=re.findall(findJudge,item)[0]
            data.append(judge)

            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

def askURL(url):
    head={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"
    }
    request=urllib.request.Request(url,headers=head)
    html=""
    try:
        response=urllib.request.urlopen(request)
        html=response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print((e.code))
        if hasattr(e,"reason"):
            print(e.reason)
    return(html)









def saveData(savepath,datalist):
    print("save...")
    book=xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet=book.add_sheet('罗宏亮船新爬虫之豆瓣电影TOP250',cell_overwrite_ok=True)
    col=("电影详细链接","图片链接","中文名","外文名","评分","评价数","概况","相关信息")
    for i in range(0,8):
        sheet.write(0,i,col[i])
    for i in range(0,250):
        print("第%d条"%(i+1))

        data=datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])

    book.save(savepath)






if __name__=="__main__":
    main()
    print("爬取完成！")

防止刚儿偷窥，战术图片诱惑