python猫眼top100实例

import requests
#导入所有Requests显式抛出的异常模块
from requests.exceptions import RequestException
from pyquery import PyQuery as pq
import json
def get_one_page(url):
    # 异常处理
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36'}
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None
#解析文本ven
def parse_one_page(html):
    doc = pq(html)
    items = doc('.main .board-wrapper dd').items()
    # 生成一个迭代器
    for item in items:
        yield {
            'index':item('.board-index').text(),
            'title':item('.board-item-main .name').text(),
            'img':item('.image-link .board-img').attr('data-src'),
            'actor':item('.board-item-main .star').text().strip()[3:],
            'releasetime':item('.board-item-main .releasetime').text().strip()[5:],
            'score':item('.board-item-main .movie-item-number .score').text()
        }

# 写入文本
def write_in_text(content):
    with open('top100.txt', 'a',encoding="utf-8") as f:
        f.write(content+'\n')
        f.close()

def main():
    for x in range(10):
        url = 'http://maoyan.com/board/4?offset='+str(x*10)
        html = get_one_page(url)
        text = parse_one_page(html)
        for item in text:
        # json.dumps 将数据转化为json格式输出，ensure_ascii中文部转码
            write_in_text(json.dumps(item,ensure_ascii=False))
        #写入进度条提示
        process = x*10+10
        print('已写入'+str(process)+'%')

if __name__ == '__main__':
    main()