python 爬取豆瓣电影top100，保存到Excel

 

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/2/7 16:23
# @Author :

from bs4 import BeautifulSoup
import re
import xlwt
import urllib.request, urllib.response, urllib.error


def default():
    baseUrl = 'https://movie.douban.com/top250?start='
    dataList = getData(baseUrl)

    savePath = '豆瓣Top250.xls'
    saveDataExcel(savePath, dataList)



def getData(baseUrl):
    """
    获取数据
    """
    findUrl = re.compile(r'<a href="(.*?)">')
    findImg = re.compile(r'<img.*src="(.*?)"')
    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)  # 忽略换行符

    dataList = []
    for i in range(0, 10):
        url = baseUrl + str(i * 25)
        html = getOneUrl(url)
        soup = BeautifulSoup(html, 'html.parser')
        for item in soup.find_all('div', class_="item"):
            data = []
            item = str(item)
            ##链接地址
            link = re.findall(findUrl, item)[0]
            data.append(link)
            img = re.findall(findImg, item)[0]
            data.append(img)
            titles = re.findall(findTitle, item)
            if len(titles) == 2 :
                cTitle = titles[0]
                oTitle = titles[1].replace('/', '')
            else:
                cTitle = titles[0]
                oTitle = ' '
            data.append(cTitle.strip())
            data.append(oTitle.strip())
            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('。', '')
            else:
                inq = ' '
            data.append(inq)
            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())
            dataList.append(data)


    return dataList

def getOneUrl(url):
    """获取一个地址信息"""
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36',
    }
    request = urllib.request.Request(url=url, headers=header)
    try:
        resp = urllib.request.urlopen(request)
        html = resp.read().decode('utf-8')
        # print(html)
    except urllib.error.HTTPError as e:
        if hasattr(e, 'code'):
            print('code', e.code)
        if hasattr(e, 'reason'):
            print('reason', e.reason)
        print('error', e)

    return html


def saveDataExcel(path, dataList):
    """保存数据到Excel"""
    print('save....')
    workbook = xlwt.Workbook(encoding='utf-8', style_compression=0) #创建workbook对象
    worksheet = workbook.add_sheet('shheet1', cell_overwrite_ok=True) #创建工作表
    col = ("链接", "图片", "中文名", "外国名", "评分", "评价数", "概况", "相关信息")
    for item in range(0, 8):
        worksheet.write(0, item, col[item]) #列名
    for item in range(0, 250):
        print("第%d条" % (item + 1))
        data = dataList[item]
        for i in range(0, 8):
            worksheet.write(item+1, i, data[i])

    workbook.save(path)
    print('over')


if __name__ == '__main__':
    default()