爬取猫眼电影最受欢迎前100 方法1

#!/usr/bin/env python
# !--*--coding:utf-8 --*--
# ![url=home.php?mod=space&uid=238618]@Time[/url]    :2018/7/5 18:08
# ![url=home.php?mod=space&uid=686208]@AuThor[/url]   TrueNewBee
# coding=utf-8
# 爬取猫眼电影
# 2018-7-5 17:37:30
# [url=http://maoyan.com/board/4?offset=0]http://maoyan.com/board/4?offset=0[/url]
'''
很完美!!!!2018-7-5 20:04:10 成功运行!啦啦啦
我觉得正则部分还可以优化有空再优化
'''

import requests
import re
import time
import json


def get_one_page(url):
    """爬取猫眼网页"""
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64)AppleWebKit/537.36 (KHTML, like Gecko)Chrome/55.0.2883.87 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    return None


def parse_one_page(html):
    """提取数据"""
    # 运用正则提取  电影名字,演员等

    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                         + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
    items = re.findall(pattern, html)
    # 遍历提取的结果生成字典
    for item in items:
        yield {
            '排名': item[0],
            '图片地址': item[1],
            '电影名字': item[2],
            '演员': item[3].strip()[3:],
            '上映时间': item[4].strip()[5:],
            '评分': item[5] + item[6]
        }


def write_to_fire(content):
    """"把提取的数据写入文件"""
    with open("猫眼Top100电影.txt", "a", encoding="utf-8") as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content, ensure_ascii=False) + '\n')  # 使用json模块实现字典的序列化


def main(offset):
    """主方法"""
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_fire(item)


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