<span>Python爬取豆瓣Top250个电影信息</span>

未修改，测试，记录第一次写爬虫

#import bs4  #网页解析，获取数据
#import re   #正则表达式，进行文字匹配
#import urllib.request,urllib.error   #制定url，获取网页数据
#import xlwt #进行excel操作
#import sqlite3  #进行SQLite数据库操作
import urllib.request, urllib.error
from bs4 import BeautifulSoup
import re
import xlwt #进行excel操作
#1.爬取网页
#2.逐一解析数据
#3.保存数据
def main():
    baseurl = "https://movie.douban.com/top250?start="

    datalist = getData(baseurl)
    # 3.保存数据
    savepath = "豆瓣电影Top250.xls"
    saveData(datalist,savepath)
    #askURL("https://movie.douban.com/top250?start=0")

#电影详情字符串匹配规则
findLink = re.compile(r'<a href="(.*?)">')
#图片规则
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)  #re.S让换行符包含在字符中
#电影名字
findTitle = re.compile(r'<span class="title">(.*)</span>')
#评分
findBating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#电影的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)
#1.爬取网页
def getData(baseurl):
    datalist = []
    #10个网页（左闭右开）
    for i in range(0,10):
        #每一页有25条电影信息
        url = baseurl + str(i*25)
        html = askURL(url)  #保存获取的网页
        # 2.逐一解析数据
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):  #查找符号的字符串，形成列表
            # print(item)
            data = [] #保存电影信息
            item = str(item)
            #电影详细的链接
            link = re.findall(findLink,item)[0]
            data.append(link)
            imgSrc = re.findall(findImgSrc,item)[0]
            data.append(imgSrc)
            titles = re.findall(findTitle, item)[0]
            data.append(titles)
            rating = re.findall(findBating,item)[0]
            data.append(rating)
            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())   #去掉前后空格
            datalist.append(data)
        #print(datalist)
    return datalist

#得到一个指定的url网页的内容
def askURL(url):
    #用户代理，告诉豆瓣访问网页的机器类型
    head = {
    "User-Agent":"Mozilla / 5.0(Windows NT 10.0; Win64;x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 75.0.3770.100 Safari / 537.36"
    }   #User-Agent不要有空格
    request = urllib.request.Request(url,headers=head)
    html=""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        #print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html

#3.保存数据
def saveData(datalist, savepath):
    workbook = xlwt.Workbook(encoding="utf-8",style_compression=0)
    worksheet = workbook.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
    col = ("电影详情","图片","名字","评分","概况","相关内容")
    for i in range(0,6):
        worksheet.write(0,i,col[i])  #列名
    for n in range(0,250):
        print("dd:%d"%n)
        data = datalist[n]
        for j in range(0,6):
            worksheet.write(n+1,j,data[j])

    workbook.save('豆瓣电影Top250.xls')

if __name__ == "__main__":    #程序执行时：
    #调用函数
    main()
    print("爬取完毕")