学习小记

# -*- coding : utf-8 -*-
#@Time    :2020/1/9 10:32
#@Author  :LI
import requests
import json
from lxml import etree
def getOnePage(n):
    url = f‘https://maoyan.com/board/4?offset={n*10}‘
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"}
    r = requests.get(url=url,headers=headers)
    return r.text
    # print(r.text)

def parse(text):
     html = etree.HTML(text)
     names = html.xpath(‘//div[@class="movie-item-info"]/p[@class="name"]/a/@title‘)
     releasetimes = html.xpath(‘//p[@class="releasetime"]/text()‘)
     item = {}
     #使用zip函数（拉链函数）
     for name,releasetime in zip(names, releasetimes):
         item[‘name‘] = name
         item[‘releasetime‘] = releasetime
         #生成器
         yield item
         #print(name,releasetime)
#保存数据
def saveData(data):
     with open(‘movie.json‘, ‘a‘, encoding=‘utf-8‘)as f:
         #将字典、列表转化为字符串
         data = json.dumps(data, ensure_ascii=False) + ‘\n‘
         f.write(data)

def run():
    for a in range(0,10):
        text = getOnePage(a)
        iteams = parse(text)
        for iteam in iteams:
            print(iteam)
            saveData(iteam)

if __name__ == ‘__main__‘:
    run()