豆瓣电影爬虫

分享一个爬虫小项目

豆瓣网电影top250
适用对象：初学者
要点知识：
① 数据过滤（正则）
② 分页
③ 数据保存
细节特么的自己看代码

#-*- codeing = utf-8 -*-
#@Time：2021/1/2814:32
#@Author：小魁
#@File：DouBan_Test.py
#@Software：PyCharm

import sys
# 正则表达式，进行文字匹配
import re
# 指定url，获取网页数据
import urllib.request,urllib.error,urllib.response
# 进行excel操作
import xlwt
# 获取数据解析网页
from bs4 import BeautifulSoup
# 数据入库
import sqlite3

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

    # 保存到excel表格
    # SavePath(datalist,savepath)

    # 保存到数据库sqlite
    SaveDatas2DB(datalist,dbpath)

    AskUrl("https://movie.douban.com/top250?start=")

# 定义一个全局变量即正则表达式的对象
findLink = re.compile(r'<a href="(.*?)">')
# 影片图片,re.S让换行符包含在字符中
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)
# 影片名
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>')
# 影片介绍
findInq = re.compile(r'<span class="inq">(.*)</span>')
# 影片相关内容
findDb = re.compile(r'<p class="">(.*?)</p>',re.S)

# 获取数据
def GetData(baseurl):
    datalist = []
    # 根据网址规律拼接url
    for i in range(0,10): # 翻页
        url = baseurl + str(i*25) # 每页25条数据，一共250条
        html = AskUrl(url) # 保存网页原码

        # 网页逐一解析
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"): # class要加下划线，因为它与系统定义的参数重名
            # print(item)
            # 保存一部电影的所有信息
            data = []
            item = str(item)
            # 提取数据
            link = re.findall(findLink,item)[0]
            data.append(link)

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

            # 电影名可能有中文外文两种名字或只有其中一种名字，需要做处理
            title = re.findall(findTitle,item)
            if(len(title)==2):
                ctitle = title[0]
                data.append(ctitle)
                # 去掉英文名前面的/，替换掉
                otitle = title[1].replace("/","")
                data.append(otitle)
            else:
                data.append(title[0])
                # 外文名留空
                data.append('')

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

            judge = re.findall(findJudge,item)[0]
            data.append(judge)

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

            db = re.findall(findDb,item)[0]
            # 去掉<br/>
            db = re.sub('<br(\s+)?/>(\s+)',"",db)
            # 替换/
            db = re.sub('/',"",db)
            # 去掉前后空格
            data.append(db.strip())
            # 将一部电影信息放入列表
            datalist.append(data)
    return datalist

# 获取指定页面的内容
def AskUrl(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36"
    }
    # 开始发送请求
    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"):
            return (e.code)
        if hasattr(e,"reason"):
            return (e.reason)
    return html

# 保存数据到excel
def SavePath(datalist,savepath):
    workbook = xlwt.Workbook(encoding='utf-8',style_compression=0)
    worksheet = workbook.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
    # 写入列名
    col = ("电影详情链接","图片链接","中文名","外文名","评分","评价数","概括","相关信息")
    for i in range(0,8):
        worksheet.write(0,i,col[i])

    # 放入打印条数
    for i in range(0,250):
        print("第%d条"%(i+1))
        # 放入打印内容
        data = datalist[i]
        for j in range(0,8):
            worksheet.write(i+1,j,data[j])

    workbook.save(savepath)

# 保存数据到数据库sqlite
def SaveDatas2DB(datalist,dbpath):
    init_db(dbpath)
    conn = sqlite3.connect(dbpath)
    cur = conn.cursor()

    for data in datalist:
        # 获取每一列
        for index in range(len(data)):
            if index == 4 or index == 5:
                continue
            # 加双引号
            data[index]  = '"'+data[index]+'"'
        sql = '''
                insert into movie250(
                    infou_link, pic_link, cname, ename, score, rated, instroduction, info
                ) values (%s)
            '''%",".join(data)
        cur.execute(sql)
        conn.commit()
    cur.close()
    conn.close()


# 创建数据库
def init_db(dbpath):
    # 建表数据表
    sql = '''
        create table movie250
        (
        id integer primary key autoincrement,
        infou_link text,
        pic_link text,
        cname varchar ,
        ename varchar ,
        score numeric ,
        rated numeric ,
        instroduction text,
        info text
        )
    
    '''
    # 拼接指引
    conn = sqlite3.connect(dbpath)
    # 创建游标
    cursor = conn.cursor()
    # 对目标数据库执行sql语句
    cursor.execute(sql)
    # 提交
    conn.commit()
    # 关闭
    conn.close()


# 当程序被执行时，调用函数，使流程都在以下可控范围内被执行
if __name__ == "__main__":
    main()
    # init_db("Tmov250.db")
    print("爬取完毕")