python爬取豆瓣top250电影源码

数据库版
#
-*- codeing=utf-8 -*- import sys from bs4 import BeautifulSoup import re import urllib.request,urllib.error import xlwt import sqlite3 #影片超链接的规则 findlink=re.compile(r'<a href="(.*?)">')#创建正则表达式对象,表示规则 #影片图片 findImgsrc=re.compile(r'<img.*src="(.*?)"',re.S)#re.S让换行符包含在字符中 #影片片名 findtitle=re.compile(r'<span class="title">(.*?)</span>') #影片评分 findRating=re.compile(r'<span class="rating_num" property="v:average">(.*?)</span>') #评价人数 findjudge=re.compile(r'<span>(\d*)人评价</span>') # 找到概况 findinq=re.compile(r'<span class="inq">(.*)</span>') #找到影片相关内容导演 findBd=re.compile(r'<p class="">(.*?)</p>',re.S) def main(): baseurl="https://movie.douban.com/top250?start=" #爬取网页 datalist=getDate(baseurl) dbpath="movie.db" saveData2DB(datalist,dbpath) #得到指定一个url的网页内容 def askurl(url): head={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36"} request=urllib.request.Request(url,headers=head) html="" try: reponse=urllib.request.urlopen(request) html=reponse.read().decode("utf-8") # print(html) except Exception as e: print(e) return html #爬取网页 def getDate(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) #获取到影片的超链接 link=re.findall(findlink,item)[0] data.append(link) imgsrc=re.findall(findImgsrc,item)[0] data.append(imgsrc) title = re.findall(findtitle, item) if (len(title)==2): ctitle=title[0]#添加中文名 data.append(ctitle) otitle=title[1].replace("/","")#去掉无关的符号 data.append(otitle)#添加外国名 else: data.append(title[0]) data.append(' ')#外国名留空 Rating = re.findall(findRating, item)[0] data.append(Rating) judge= re.findall(findjudge, item)[0] # print(judge) data.append(judge) inq = re.findall(findinq, item) if len(inq)!=0: inq=inq[0].replace("","") data.append(inq) else: data.append(inq) 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 #保存数据 def saveData(datalist,savepath): book=xlwt.Workbook(encoding="utf-8") sheet=book.add_sheet('豆瓣电影top250',cell_overwrite_ok=True) col=('电影详情连接',"图片连接","影片中文名","影片外国名","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): print("第%d条"%(i+1)) data=datalist[i] for j in range(0,8): sheet.write(i+1,j,data[j]) book.save('豆瓣电影Top250.xls') def saveData2DB(datalist,dbpath): init_db(dbpath) conn=sqlite3.connect(dbpath) cur=conn.cursor() try: for data in datalist: for index in range(len(data)): if index==4 or index==5: continue data[index] = '"' + str(data[index]) + '"' sql=''' insert into movie250( info_link,pic_link,cname,ename,score,rated,instrduction,info) values(%s) '''%",".join(data) print(sql) cur.execute(sql) conn.commit() cur.close() conn.close() print("写入数据库成功") except Exception as e: print(e) def init_db(dbpath): conn = sqlite3.connect(dbpath) cursor=conn.cursor() sql = ''' create table movie250 ( id integer primary key autoincrement, info_link text, pic_link text, cname varchar, ename varchar, score numeric, rated numeric, instrduction text, info text ) ''' # 创建数据表 cursor.execute(sql) conn.commit() conn.close() if __name__=="__main__": baseurl="https://movie.douban.com/top250?start=" datalist=getDate(baseurl) dbpath="movie.db" saveData2DB(datalist,dbpath) print("爬取成功")
excel版
#-*- codeing=utf-8 -*-
import sys
from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt
import sqlite3
#影片超链接的规则
findlink=re.compile(r'<a href="(.*?)">')#创建正则表达式对象,表示规则
#影片图片
findImgsrc=re.compile(r'<img.*src="(.*?)"',re.S)#re.S让换行符包含在字符中
#影片片名
findtitle=re.compile(r'<span class="title">(.*?)</span>')
#影片评分
findRating=re.compile(r'<span class="rating_num" property="v:average">(.*?)</span>')
#评价人数
findjudge=re.compile(r'<span>(\d*)人评价</span>')
# 找到概况
findinq=re.compile(r'<span class="inq">(.*)</span>')
#找到影片相关内容导演
findBd=re.compile(r'<p class="">(.*?)</p>',re.S)


def main():
    baseurl="https://movie.douban.com/top250?start="
    #爬取网页
    datalist=getDate(baseurl)
    savepath=".\\豆瓣电影Top250表格版.xls"
    saveData(datalist,savepath)


#得到指定一个url的网页内容
def askurl(url):
    head={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36"}
    request=urllib.request.Request(url,headers=head)
    html=""
    try:
        reponse=urllib.request.urlopen(request)
        html=reponse.read().decode("utf-8")
        # print(html)
    except Exception as e:
        print(e)
    return html

#爬取网页
def getDate(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)
            #获取到影片的超链接
            link=re.findall(findlink,item)[0]
            data.append(link)

            imgsrc=re.findall(findImgsrc,item)[0]
            data.append(imgsrc)

            title = re.findall(findtitle, item)
            if (len(title)==2):
                ctitle=title[0]#添加中文名
                data.append(ctitle)
                otitle=title[1].replace("/","")#去掉无关的符号
                data.append(otitle)#添加外国名
            else:
                data.append(title[0])
                data.append(' ')#外国名留空

            Rating = re.findall(findRating, item)[0]
            data.append(Rating)

            judge= re.findall(findjudge, item)[0]
            # print(judge)
            data.append(judge)

            inq = re.findall(findinq, item)
            if len(inq)!=0:
                inq=inq[0].replace("","")
                data.append(inq)
            else:
                data.append(inq)

            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

#保存数据
def saveData(datalist,savepath):
    book=xlwt.Workbook(encoding="utf-8")
    sheet=book.add_sheet('豆瓣电影top250',cell_overwrite_ok=True)
    col=('电影详情连接',"图片连接","影片中文名","影片外国名","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):
        print("第%d条"%(i+1))
        data=datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])
    book.save('豆瓣电影Top250表格版.xls')


def saveData2DB(datalist,dbpath):
    init_db(dbpath)
    conn=sqlite3.connect(dbpath)
    cur=conn.cursor()
    try:
        for data in datalist:
            for index in range(len(data)):
                if index==4 or index==5:
                    continue
                data[index] = '"' + str(data[index]) + '"'
            sql='''
                    insert into movie250(
                    info_link,pic_link,cname,ename,score,rated,instrduction,info)
                    values(%s)
                    '''%",".join(data)
            print(sql)
            cur.execute(sql)
            conn.commit()
        cur.close()
        conn.close()
        print("写入数据库成功")
    except Exception as e:
        print(e)




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

    )
    '''  # 创建数据表
    cursor.execute(sql)
    conn.commit()
    conn.close()

if __name__=="__main__":
    main()
    print("爬取成功")

 

posted @ 2021-09-24 14:08  我有清茶与酒  阅读(183)  评论(0编辑  收藏  举报