Python练手项目

准备工作
通过浏览器查看分析目标网页 ,学习编程基础规范。
获取数据
通过HTTP库向目标站点发起请求,请求可以包含额外的header等信息，如果服务器能正常响应,会得到一个Response ,便是所要获取的页面内容。
解析内容
得到的内容可能是HTML、 json等格式,可以用页面解析库、正则表达式等进行解析。
保存数据
保存形式多样,可以存为文本,也可以保存到数据库,或者保存特定格式的文件。

# -*- codeing = utf-8 -*-
# @Time : 2021/2/10 20:28

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  #知道URL，获取网页数据
import xlwt                         #进行excel操作
import sqlite3                      #进行SQLLite数据库操作

def mian():
    baseurl = "https://movie.douban.com/top250?start="
    #1.爬取网页
    dataList = getData(baseurl)
    print(dataList)
    #保存到Excel
    # savepath = "豆瓣电影TOP250.xls"
    # saveDate(dataList,savepath)
    #保存到数据库
    dbpath = "movie.db"
    saveDate2DB(dataList,dbpath)


#影片详情链接的规则（获取的是正则表达式的内容）
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串中
#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>(.*)人评价</span>')
#概况
findIng = 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(0,25):
        url = baseurl + str(i*25)
        html = askURL(url)

        # 2.解析数据
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):
            # print(item) #测试，查看电影全部信息
            data = []
            item = str(item)

            link = re.findall(findLink,item)[0] #re库通过正则表达式查找指定的字符串
            data.append(link)

            imgSrc = re.findall(findImgSrc,item)[0]
            data.append(imgSrc)

            titles = re.findall(findTitle,item)     #片名可能只有一个中文名，没有英文名
            if(len(titles) == 2):
                ctitle = titles[0]
                data.append(ctitle)                 #中文名
                otitle = titles[1].replace("/","")  #去掉无关符号
                data.append(otitle)                 #英文名
            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(findIng, 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) #去掉<br/>
            bd = re.sub('/'," ",bd)                 #替换/
            data.append(bd.strip())                 #去掉前后空格

            dataList.append(data)
    print(dataList)
    return dataList

#3.保存数据到Excel
def saveDate(dataList,savepath):
    book = xlwt.Workbook(encoding="utf-8",style_compression=0)  # 创建worksheet对象
    sheet = book.add_sheet('豆瓣top250',cell_overwrite_ok=True)  # 创建工作表
    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])
    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(savepath)  # 保存数据表

#保存到数据库
def saveDate2DB(dataList, dbpath):
    init_db(dbpath)                 #创建数据库
    conn = sqlite3.connect(dbpath)  
    cur = conn.cursor()

    for data in dataList:
        for i in range(len(data)):
            if i == 4 or i == 5:
                continue
            data[i] = '"'+data[i]+'"'
        sql = ''' 
            insert into movie250(
                info_link, pic_link ,cname ,ename ,score ,rated ,instroduction ,info)
            values(%s)'''%",".join(data)
        #print(sql)
        cur.execute(sql)
        conn.commit()
    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)  #打开或创建SQLlite数据库 
    cursor = conn.cursor()          #获取数据库游标
    cursor.execute(sql)             #执行SQL语句
    conn.commit()                   #提交数据库操作
    conn.close()                    #关闭数据库连接


my_headers = [
    "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
    'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
    'Opera/9.25 (Windows NT 5.1; U; en)',
    'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
    'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
    'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
    'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
    "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
    "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
]

#得到一个网页的内容
def askURL(url):
    head = {
        "user-agent": "Opera/9.25 (Windows NT 5.1; U; en)"  #若报403错误，是因为网站防爬虫，换一个请求头部，或者换个网
    }
    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__":      #当程序执行时
    mian()
    print("保存完毕！")