Python 爬取豆瓣电影Top250

# author: JaChen
# datetime: 2021/11/19 20:55
# @File: 3.py
# func:


import re   # 正则表达式 进行文字匹配
from random import random

from bs4 import BeautifulSoup  # 网页解析 获取数据
import urllib.request, urllib.error   # 制定URL 获取网页数据
import xlwt   # 进行excel 操作
import sqlite3   # 进行SQLite数据库操作  无需引入直接用
def main():
    baseurl = "https://movie.douban.com/top250?start="
    # 1.爬取数据
    datalist = getData(baseurl)
    savepath = "豆瓣电影Top250.xls"
    saveData(datalist, savepath)
    # askURL("https://movie.douban.com/top250?start=")

findLink = re.compile(r'<a href="(.*?)">')   # 创建正则表达式对象 表示规则（字符串模式）
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)  # 让换行包含在字符中
findTitle = re.compile(r'<span class="title">(.*)</span>')
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
findJudge = re.compile(r'<span>(\d*)人评价</span>')
findInq = re.compile(r'<span class="inq">(.*)</span>')
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)

# proxy_list=[#这是我当时用的代理IP，请更新能用的IP
#     '202.106.169.142:80',
#     '220.181.35.109:8080',
#     '124.65.163.10:8080',
#     '117.79.131.109:8080',
#     '58.30.233.200:8080',
#     '115.182.92.87:8080',
#     '210.75.240.62:3128',
#     '211.71.20.246:3128',
#     '115.182.83.38:8080',
#     '121.69.8.234:8080',
#         ]
# #接着在你使用的到urllib2的代码中，绑定某个IP，如下：
# proxy       = random.choice(proxy_list)
# urlhandle   = urllib2.ProxyHandler({'http':proxy})
# opener      = urllib2.build_opener(urlhandle)
# urllib2.install_opener(opener)
#
# #正常使用urllib
# req         = urllib2.Request(listurl, headers=headers)
# content     = urllib2.urlopen(req).read()

# 1.爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0, 10):   # 调用获取页面信息的函数，10次
        url = baseurl + str(i*25)
        html = askURL(url)   # 保存获取到的一页源码
        # 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 形成链表
            data = []   # 保存一部电影的全部信息
            item = str(item)
            # print(item)
            Link = re.findall(findLink, item)[0]   # re库用来通过正则表达式查找指定的字符串
            data.append(Link)
            # print(Link)
            ImgSrc = re.findall(findImgSrc, item)[0]
            data.append(ImgSrc)    # 添加图片
            Title = re.findall(findTitle, item)   # 片名可能只有一个中文名
            if(len(Title) == 2):
                cTitle = Title[0]
                data.append(cTitle)
                oTitle = Title[1].replace("/", "")  # 去掉无关符号
                data.append(oTitle)
            else:
                data.append(Title[0])
                data.append(' ')

            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:
                Inq = Inq[0].replace("。", "")  # 去掉句号
                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)
            # Bd = re.sub('\n', " ", Bd)
            data.append(Bd.strip())    # 去掉前后空格

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


# 得到指定一个URL的网页内容
def askURL(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Mobile Safari/537.36"
    }  # 告诉服务器我们是什么类型的服务器
    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


# 3.存储数据
def saveData(datalist, savepath):
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象
    sheet = book.add_sheet('豆瓣电影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])  # 列名
    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)

if __name__ == "__main__":
    #  调用函数
    main()
    print("爬取完毕！")