Python爬虫学习汇总

Python / 2021年5月23日 / hamster

from bs4 import BeautifulSoup  # 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 mysql.connector  #进行mysql数据库操作


def main():
    baseurl = "https://movie.douban.com/top250?start="
    #1 爬取网页
    #2 解析数据
    datalist = getData(baseurl)
    #3 保存数据
    savepath = "douban.xls"
    saveData(datalist,savepath)
    #4 保存数据库
    saveDataDB(datalist)


# 影片详情链接的规则
findLink = re.compile(r'<a href="(.*?)">')
# 影片图片
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)
# 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>')
# 概括
findInq = re.compile(r'<span class="inq">(.*)</span>')
# 相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)


# 爬取网页
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)
            data = []
            item = str(item)

            #影片链接
            link = re.findall(findLink,item)[0]
            data.append(link)

            #影片图片
            imgSrc = re.findall(findImgSrc,item)[0]
            data.append(imgSrc)

            #影片片名
            titles = re.findall(findTitle,item)
            if len(titles) == 2:
                #添加中文名
                ctitle = titles[0]
                data.append(ctitle)
                #添加外国名
                otitle = titles[1].replace("/","")
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')

            # 影片评分
            rating = re.findall(findRating,item)[0]
            data.append(rating)

            #影片评价人数
            judgeNum = re.findall(findJudge,item)[0]
            data.append(judgeNum)

            #影片概述
            inq = re.findall(findInq,item)
            if len(inq) != 0:
                inq = inq[0].replace("。","")
                data.append(inq)
            else:
                data.append(" ")

            #相关内容
            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?'," ",bd)  #去掉<br/>
            bd = re.sub('/'," ",bd)  #去掉/
            data.append(bd.strip())  #去掉空格

            datalist.append(data)
    #print(datalist)
    return datalist


# 保存数据
def saveData(datalist,savepath):
    book = xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet = book.add_sheet('豆瓣电影',cell_overwrite_ok=True)
    col = ("电影链接","图片链接","影片中文名","外国名","评分","评论数","概括","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)

# 保存数据到数据库
def saveDataDB(datalist):
    mydb = mysql.connector.connect(host="127.0.0.1", user="root", passwd="", database="python_db")
    mycursor = mydb.cursor()

    sql = "INSERT INTO test2 (url,img,ctitle,otitle,soc,num,inq,bd) VALUES (%s,%s,%s,%s,%s,%s,%s,%s)"
    val = []
    for i in range(len(datalist)):
        val.append(tuple(datalist[i]))

    mycursor.executemany(sql, val)
    mydb.commit()
    mycursor.close()
    mydb.close()


# 得到指定一个URL的网页内容
def askURL(url):
    #模拟浏览器的头部信息，向服务器发送消息
    head = {}
    #用户代理，表示告诉服务器我们是什么类型的机器，本质上是告诉浏览器我们可以接受什么水平的信息
    head["User-Agent"] = "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36"
    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



if __name__ == '__main__':
    main()

excel, mysql, urllib, 正则表达式, 爬虫