Python爬取豆瓣电影TOP250，结果输出为Execl，保存海报图片。

使用requests获取网页内容，beautifulsoup煲汤，xlsxwriter导出excel表格。完全是新手练习作品，欢迎交流。

import requests as req
import bs4
import xlsxwriter as xs
import os

def get_content(page_url): #获取网页
    url = page_url
    r = []
    headers = {'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Mobile Safari/537.36'}
    for each in url:
        r.append(req.get(each, headers = headers))
    return r

def analysis_content(html):  #分析网页
    global image_url
    movies = []
    image_url = {}  #存储图片名字 图片url
    movies_all = {}
    douban = html
    #此处douban是一个列表，存储pages个网页的内容
    for each in douban:
        soup = bs4.BeautifulSoup(each.text,'html.parser') #注意是each.text
        div_info = soup.find_all('div',class_='info')
        for each in div_info:
            movies_name = each.a.span.text
            star = each.find('span', class_ = 'rating_num') #评分
            movies_star = star.text
            movies.append(movies_star)
            quote = each.find('span', class_ = 'inq')  #评论
            try:  # 防止quote不存在报错
                movies_quote = quote.text
            except:
                movies_quote = ' '
            movies.append(movies_quote)
            movies_all[movies_name] = movies
            movies = []   #列表清空，不然数据会累加
            
        div_items = soup.find_all('div', class_='item') #用于下载海报
        for each in div_items:
            image_url[each.img['alt']] = each.img['src']
        
    return movies_all

def how_many_pages():   # 爬取深度
    pages_url = []
    pages = input('How many pages do you want to scrap?(total:10):')
    for i in range(0,int(pages)):
        pages_url.append('https://movie.douban.com/top250?start='+ str(25*(int(i))) +'&filter=')
    return pages_url

def excel_export(movies_all): # 输出为excel
    workbook = xs.Workbook('Top250Movies.xlsx')
    worksheet = workbook.add_worksheet()
    text_format = workbook.add_format({'center_across':'True','text_wrap':'True'})
    capture_format = workbook.add_format({'bold':'Ture','center_across':'True'})
    worksheet.set_column(1 ,5 ,20)
    
    worksheet.write('A1', '排名', capture_format)
    worksheet.write('B1', '名字', capture_format)
    worksheet.write('C1', '评分', capture_format)
    worksheet.write('D1', '评论', capture_format)
    row = 1      #从第二行第一列开始写
    col = 0
    i = 1       #排名
    
    for name in movies_all:    # movies_all 含有所有电影数据的字典
        worksheet.write(row, col, i, text_format)
        worksheet.write(row, col+1, name, text_format)
        worksheet.write(row, col+2, movies_all[name][0] , text_format)
        worksheet.write(row, col+3, movies_all[name][1], text_format)
        row += 1
        i += 1
    workbook.close()

def image_save():
    folder = '豆瓣top250'
    g = 1
    try:   #防止出现同名文件夹
        os.mkdir(folder)
    except:
        folder = '豆瓣top250(' + str(g) +')'
        g += 1
    os.chdir(folder)
    
    for name in image_url:
        with open(name+'.jpg', 'wb') as f:
            img_html = req.get(image_url[name])
            f.write(img_html.content)

            

def main():
    page = how_many_pages()
    html = get_content(page)
    movies = analysis_content(html)
    excel_export(movies)
    print('表格输出完成!')
    image_save()
    print('图片输出完成!')
    

if __name__ == "__main__":
    main()