python爬虫从入门到放弃（九）之 Requests+正则表达式爬取猫眼电影TOP100

python爬虫从入门到放弃（九）之 Requests+正则表达式爬取猫眼电影TOP100

import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool

def get_one_page(url):
    headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Safari/537.36'}
    try:
        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].strip(),
        'actor': item[3].strip()[3:] ,#if len(item[3]) > 3 else '',
        'time': item[4].strip()[5:] ,#if len(item[4]) > 5 else '',
        'score': item[5].strip() + item[6].strip()
        }

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(i * 10)
# 多线程方法
    pool =Pool()#多线程会打乱数据的顺序
    # 声明一个进程池
    pool.map(main,[i*10 for i in range(10)]) # 利用map函数
    pool.close()

 

posted @ 2018-09-19 21:49 Knight-Tao 阅读( ...) 评论( ...) 编辑 收藏