爬虫③

将数据爬取到mysql中

#@Time : 2021/5/1117:17
#@File : ConnectMysql.py
import pymysql
# def creatTable():
#     #创建连接
#     conn = pymysql.connect(host="localhost",
#                          port=3306,
#                          user="root",
#                          passwd="Ys04050016",
#                          database="movies",
#                          charset="utf8")
#
#     cursor = conn.cursor()
#     sql='''
#             create table movie250
#             (
#                 id integer primary key AUTO_INCREMENT,
#                 info_link text,
#                 pic_link text,
#                 cname varchar(255),
#                 ename varchar(255),
#                 score numeric,
#                 rated numeric,
#                 introduction text,
#                 info text
#             )
#         '''
#     cursor.execute(sql)
#     conn.commit()
#     cursor.close()
#     conn.close()
def connect():
    conn = pymysql.connect(host="localhost",
                           port=3306,
                           user="root",
                           passwd="Ys04050016",
                           database="movies",
                           charset="utf8")
    return conn
def close(conn,cursor):
    cursor.close()
    conn.close()
def creatTable():
    conn=connect()
    cursor = conn.cursor()
    sql = '''
               create table movie250
               (
                   id integer primary key AUTO_INCREMENT,
                   info_link text,
                   pic_link text,
                   cname varchar(255),
                   ename varchar(255),
                   score numeric,
                   rated numeric,
                   introduction text,
                   info text
               )
           '''
    cursor.execute(sql)
    conn.commit()
    close(conn,cursor)

#@Time : 2021/5/522:10
#@File : spiderToDataBase.py
#@Time : 2021/5/214:40
#@File : spider.py
from bs4 import BeautifulSoup
import re

import urllib.request,urllib.error
import  xlwt
import _sqlite3
import  ConnectMysql
# 指定电影网址的正则表达式
findLink=re.compile(r'<a href="(.*?)">')#r是防止错误解析/
#找图片 re.s是为了让换行符包含在字符内
findImgSrc=re.compile(r'<img.*src="(.*?)"',re.S)
#片名
findTitle=re.compile(r'<span class="title">(.*)</span>')
#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>')
#影片概况
findInq=re.compile(r'<span class="inq">(.*)</span>')
#影片简介
findBd=re.compile(r'<p class="">(.*?)</p>',re.S)

def main():
    baseUrl="https://movie.douban.com/top250?start="
    #1.爬取网页
    dataList=getData(baseUrl)
    #
    #3.保存数据
    saveDataToDB(dataList)
#爬取网页
def getData(baseUrl):
    dataList = []
    for i in range(0,10):
        url=baseUrl+str(i*25)
        html=askURL(url)
        #2.逐一解析数据
        soup=BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):#查找符合要求的字符串，形成列表
                #print(item)查看
                data=[]
                item=str(item)

                link=re.findall(findLink,item)[0]# 这个是图片超链接。re库通过正则表达式来查找指定的字符串(标准，串)
                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("")#留空

                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:
                    data.append(inq[0])
                else:
                    data.append(" ")


                bd = re.findall(findBd, item)[0]
                bd = re.sub('<br(1s+)?/>(ls+)?', " ", bd)  # 去除br
                bd = re.sub('/', " ", bd)  # 替换
                data.append(bd.strip())  # 去掉空格
                dataList.append(data)

    #print(dataList)

    return dataList

#指定一个URL网页内容
def askURL(url):
    head={
         # User-Agent中间没用空格！
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0;WOW64) AppleWebKit / 537.36(KHTML, like   Gecko) Chrome/84.0.4147.89 Safari/537.36    SLBrowser/7.0.0.4071 SLBChan/21"
    }
    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

#保存数据
def saveDataToDB(datalist):

    init_db()
    conn=ConnectMysql.connect()
    cur=conn.cursor()
    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,introduction,info
            )
            value(%s)'''%",".join(data)
        cur.execute(sql)
        conn.commit()
    ConnectMysql.close(conn,cur)
#创建数据库
def init_db():
    #在ConnectMysql.py中已经创建
    ConnectMysql.creatTable()

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

其中有个小问题 那个 inq是个集合所以添加的时候 要些inq[0]

改了挺长时间的bug 终于成功了 (^▽)