Python实现的爬取豆瓣电影信息功能案例

def getpage(url):
  try:
    res=requests.get(url)
    if res.status_code==200:
      return res.text
    return None
  except RequestException:
    return None

def parsepage(html):
  pat=re.compile('<li>.*?<em class="">(.*?)</em>.*?<img width="100" alt="(.*?)" src=.*?<p class="">'
          +'(.*?)</p>.*?property="v:average">(.*?)</span>.*?<span class="inq">(.*?)</span>.*?</li>',re.S)
  items=re.findall(pat,html)
  for item in items:
    yield{
      'index':item[0],
      'title':item[1],
      'stars':item[2].strip(),
      'score':item[3],
      'concept':item[4]
    }

def write_tofile(content):
  with open('doubanfilms.txt','a',encoding='utf-8' ) as f:
    f.write(json.dumps(content,ensure_ascii=False)+'\n')
    f.close()

def main():
  url="https://movie.douban.com/top250?"
  for i in range(0,9):
    url_i=url+'start='+str(25*i)
    html_i=getpage(url_i)
    for item in parsepage(html_i):
      print(item)
      write_tofile(item)
if __name__ == '__main__':
  main()

def main(start):
  url="https://movie.douban.com/top250?start="+str(start)
  html=getpage(url)
  for item in parsepage(html):
    print(item)
    write_tofile(item)
if __name__ == '__main__':
  for i in range(10):
    main(i*10)

#在最开始加载Pool包
from multiprocessing import Pool
#最后的执行段改为：
if __name__ == '__main__':
  for i in range(10):
    main(i*10)
  pool=Pool() #在循环外写
  pool.map(main,[i*10 for i in range (10)])