爬虫 利用正则表达式爬取猫眼电影

# coding=utf-8
import requests
import re
import json
from io import open
#from multiprocessing import Pool
from requests.exceptions import RequestException
headers = {'User-Agent':'Mozilla/5.0 '}
def get_one_page(url):
   try:
       res = requests.get(url,headers = headers)
       if res.status_code == 200:
           #print res.text
           print url
           return res.text
       return None
   except RequestException:
       return None

def parse_one_page(html):
   #pattern = re.compile('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                        #+'.*?integer">(.*?).*?fraction">(.*?).*?
',re.S)
   #items = re.findall(pattern,html)
   items=re.findall(r'
.*?class="board-index board-index-.*?
',html,re.S)
   print items
   content=[]
   for item1 in items:
       item=re.search(r'
.*?i class="board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                        +'.*?integer">(.*?).*?fraction">(.*?).*?
',item1,re.S)
       li={}
       li['index']=item.group(1)
       li['image'] = item.group(2)
       li['title'] = item.group(3)
       li['actor'] = item.group(4).strip()[3:]
       li['time'] = item.group(5).strip()[5:]
       li['score'] = item.group(6)+item.group(7)
       content.append(li)

   #print content
   return content
       #yield{
           #'index': item[0],
           #'image': item[1],
           #'title': item[2],
           #'actor': item[3].strip()[3:],
           #'time': item[4].strip()[5:],
           #'score': item[5] + item[6]
       #}


def write_to_file(content):
    with open ('res.txt', 'a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False))
        f.close()


def main():
    for i in range(0,10):
        url = 'http://maoyan.com/board/4?offset=' + str(i*10)
        html = get_one_page(url)
        content=parse_one_page(html)
        print content
   #for item in parse_one_page(html):
       #print(item)
        write_to_file(content)

if __name__ == '__main__':
    #p = Pool()
    #p.map(main, [i * 10 for i in range(10)])
    main()