前言：最近正在學習python爬蟲,瞭解一些基礎知識後，還是要實踐動手熟悉。下面文章例子有空再加備註。。

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


def get_one_page(url):
    try:
        headers = {'User-Agent': 'User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'}
        response = requests.get(url, headers = headers)
        #response.raise_for_status()
        #response.encoding = response.apparent_encoding ('utf-8')
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i.*?fraction">(.*?)</i>.*?</dd>', 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(),
            'time':  item[4].strip(),
            'score': item[5].strip() + item[6].strip()
        }


#       字典寫入檔案
def write_to_json(content):
    with open('result.txt', 'a', encoding='utf-8') as f:
        print(type(json.dumps(content)))
        #       dumps方法實現字典序列化
        f.write(json.dumps(content, ensure_ascii=False,).encode('utf-8').decode('utf-8') + '\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):
        write_to_json(item)


if __name__ == '__main__':
    for i in range(10):
        main(offset=i * 10)
        #       延時等待，貓眼反爬蟲，速度過快，無響應
        time.sleep(1)