记一次python爬虫实战，豆瓣电影Top250爬虫

 import requests
 from bs4 import BeautifulSoup
 import re
 import traceback

 def GetHtmlText(url):
     for i in range(0,1):        #尝试两次
         try:
             r=requests.get(url)
             r.encoding = 'utf-8'
             r.raise_for_status();
             return r.text;
         except:
             traceback.print_exc()
             continue
     return 

 def GetMovieInfo(url):
     movieDict={}
     for page in range(0,10):
         try:
             page_url = '?start='+str(page*25)
             html = GetHtmlText(url+page_url)
             Soup = BeautifulSoup(html, 'html.parser')
             movie = Soup.find(name="ol",class_='grid_view') #所有电影信息
             movieList = movie.find_all(name='li')  #电影信息列表
             for single in movieList:        #循环单页的电影信息
                 num = single.find(name='em').string    #电影排名
                 title1 = single.find_all(name='span',class_='title')
                 title2 = single.find(name='span',class_='other').string
                 if len(title1)==2:
                     movieTitle = title1[0].string+title1[1].string+title2.string
                 else:
                     movieTitle = title1[0].string+title2.string
                 classBD = single.find(name='div',class_='bd').contents    #我也不知道为什么bs给我返回7个节点
                 movieActor = classBD[1].text
                 movieRating = re.findall(r'\d?\.\d?',str(classBD[3]))[0]
                 movieQuote = classBD[5].text
                 movieDict['num'] = num
                 movieDict['movieTitle'] = movieTitle
                 movieDict['actor'] = movieActor
                 movieDict['rating'] = movieRating
                 movieDict['quote'] = movieQuote
                 printMovieInfo(movieDict)
         except:
             traceback.print_exc()

 def printMovieInfo(Info):
     try:
         with open('/home/why/py/movieInfo.txt','a',encoding='utf-8') as f:
             f.write(str(Info['num']+Info['movieTitle']+'\n'+Info['actor']+'\n评分:'+Info['rating']+'\n评价：'+Info['quote']+'\n'))
     except:
         traceback.print_exc()

 def main():
     base_url = 'https://movie.douban.com/top250'
     GetMovieInfo(base_url)
 main()

结果：