Java转python学习笔记-爬虫-实战豆瓣250-datebase

from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt
import sqlite3

def main():
    baseurl = 'https://movie.douban.com/top250?start='
    datalist = getData(baseurl)
    # savepath = "豆瓣电影Top250.xls"
    # saveData(datalist,savepath)
    dbpath = 'movie.db'
    saveDataDb(datalist,dbpath)

findLink = re.compile(r'<a href="(.*?)">')#具体规则
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)#re.S忽略换行符
findTitle = re.compile(r'<span class="title">(.*?)</span>')
findRate = 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)
        # 解析数据
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):
            # print(item)
            date = []
            item = str(item)
            Link = re.findall(findLink,item)[0]
            date.append(Link)
            Image = re.findall(findImgSrc,item)[0]
            date.append(Image)
            Title = re.findall(findTitle,item)
            if(len(Title)==2):
                ctitle = Title[0]
                date.append(ctitle)
                otitle = Title[1].replace("\xa0",'').replace("/",'')#去掉无关的符号
                date.append(otitle)
            else:
                date.append(Title[0])
                date.append(' ')#没有外文名留空
            Rate = re.findall(findRate, item)[0]
            date.append(Rate)
            Judge = re.findall(findJudge, item)[0]
            date.append(Judge)
            Inq = re.findall(findInq, item)
            if(len(Inq)!=0):
                Inq = Inq[0].replace("。",'')
                date.append(Inq)
            else:
                date.append(" ")
            Bd = re.findall(findBd, item)[0]
            Bd = re.sub('<br(\s+)?/>(\s+)?',' ',Bd)#去掉br
            Bd = Bd.lstrip().rstrip().replace("/",'').replace("...",'').replace("\xa0",'')
            date.append(Bd)
            datalist.append(date)#把一部电影信息加入
    return datalist

def askURL(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    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

def saveData(datalist,savepath):
    print('save..')
    import xlwt
    book = xlwt.Workbook(encoding='utf-8',style_compression=0)#样式压缩效果
    sheet = book.add_sheet('豆瓣电影Top250.xls',cell_overwrite_ok=True)  # 创建工作表覆盖内容
    col = ['电影详情链接','图片链接','影片中文名','影片外国名','评分','评价数','概况','相关信息']
    for i in range(0,8):
        sheet.write(0,i,col[i])#列名
    for i in range(0,250):
        print('第{}条'.format(i+1))
        date = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,date[j])

    book.save(savepath)

def saveDataDb(datalist,dbpath):
    init_db(dbpath)
    conn = sqlite3.connect(dbpath)
    cur = conn.cursor()

    for data in datalist:
        for index in range(len(data)):
            if(index == 4 or index == 5):
                continue
            data[index] = '"' + data[index] + '"'#给原值加上引号
        sql = '''
            insert into movie250(
            info_link,pic_link,cname,ename,score,rated,instroduction,info)
            values(%s)'''%",".join(data)#用逗号分隔
        # print(sql)
        cur.execute(sql)
        conn.commit()
    cur.close()
    conn.close()

def init_db(dbpath):
    sql = """
        create table movie250
        (
        id integer primary key autoincrement,
        info_link text,
        pic_link text,
        cname varchar,
        ename varchar,
        score numeric,
        rated numeric,
        instroduction text,
        info text
        )
    """
    conn = sqlite3.connect(dbpath)
    curse = conn.cursor()
    curse.execute(sql)
    conn.commit()
    conn.close()

if __name__ == '__main__':
    main()
    # askURL('https://movie.douban.com/top250?start=0')
    # init_db("movetest.db")
    print('爬取完毕')