电影top250爬虫获取

1. 问题

爬取某瓣电影top250的基本介绍信息。

2. 思路确立

2.1 准备工作

2.2 获取数据

2.3 解析内容 

2.4 保存数据

3. 代码实现

​
# -*- coding = utf-8 -*-
# @Time : 2021/10/22 13:47
# @Author : OneLock
# @File : spider.py
# @Software : PyCharm

from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt

def main():
    baseurl = "https://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = "top250.xls"
    saveDate(datalist,savepath)

findLink = re.compile(r'<a href="(.*?)">')
findImgSrc = 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 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)

            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


def askURL(url):
    head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36 Edg/95.0.1020.30"}
    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 saveDate(datalist,savepath):
    book = xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet = book.add_sheet("top250",cell_overwrite_ok=True)
    col = ("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):
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])
    book.save(savepath)



if __name__ == "__main__" :
    main()
    print("完结撒花")

​