requests爬猫眼电影 -- 记录

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import requests
import re
from requests.exceptions import RequestException
from json import dumps

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

def parse_one_page(html):
    pattern = re.compile('
.*?"board-index.*?>(.*?).*?data-src="(.*?)".*?/>.*?name">(.*?)'
                         +'
.*?star">(.*?)
.*?releasetime">(.*?)
.*?integer">(.*?)'
                          +'.*?fraction">(.*?).*?
',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            'index' :item[0],
            'picurl' :item[1],
            'title' :item[2],
            'actor' :item[3].replace('\n','').strip(),
            'times' :item[4],
            'score' :item[5] + item[6]
        }

def write_to_file(content):
    with open('movie.txt','a',encoding='utf8') as fp:
        fp.write(dumps(content,ensure_ascii=False) + '\n')

def main(offset):
    url = "http://maoyan.com/board/4?offset=%s" % offset
    html = get_one_page(url)
    for item in parse_one_page(html):
        write_to_file(item)

if __name__ == '__main__':
    for i in range(10):
        main(i * 10)