python爬虫练习--爬取猫眼top100电影信息

#! /usr/bin/env python
# coding: utf-8
#环境要求：python3
#抓取猫眼电影top100
'''
抓取的目标网站为：http://maoyan.com/board/4
页面中显示的有效信息有影片名称、主演、上映时间、上映地区、评分、图片等信息
点击下一页发现url会变成http://maoyan.com/board/4?offset=30，主要增加了offset参数，
且规律是0，10，20，30
'''

import json
import requests
from requests.exceptions import RequestException
import re
import time

#抓取首页
def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.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)

    for item in items:
        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('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')


def main(offset):
    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_file(item)


if __name__ == '__main__':
    for i in range(10):
        main(offset=i * 10)
        time.sleep(1)
 

 

转载于:https://www.cnblogs.com/watchslowly/p/9122486.html