#!/usr/bin/python3
# -*- coding: utf-8 -*-
# @Time    : 2021/9/7 9:35
# @Author  : Sun
# @Email   : 8009@163.com
# @File    : sun_test.py
# @Software: PyCharm


import requests
from lxml import etree


def get_web_content():
    try:
        url = "htpps://***keyword=%E6%97%A0%E9%92%A2%E5%9C%88&wq=%E6%97%A0%E"
  "9%92%A2%E5%9C%88&ev=1_68131%5E&pvid=afbf41410b164c1b91d"
        "abdf18ae8ab5c&page=5&s=116&click=0 "
        header = {
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64)"
            "AppleWebKit/537.36 (KHTML, like Gecko) "
                          "Chrome/75.0.3770.100 Safari/537.36 "}
        response = requests.request(method="Get", url=url, headers=header)
        result = response.text
        return result
    except TimeoutError as e:
        return None


def parsing():
    result = get_web_content()
    if result is not None:
        html = etree.HTML(result)
        # 先獲取一個(gè)大的節(jié)點(diǎn)，包含了想要獲取的所有信息
        ii = html.xpath('//*[@id="J_goodsList"]/ul/li')
       
        for _ in ii:
        # 采用循環(huán)，依次從大節(jié)點(diǎn)中獲取小的節(jié)點(diǎn)內(nèi)容
            # ''.join() 將列表中的內(nèi)容拼接成一個(gè)字符串
            infoResult = {
            	# @href 表示：獲取屬性為href的內(nèi)容
                'href': "https:" + _.xpath('./div/div[1]/a/@href')[0],
                'title': ''.join(
                        _.xpath('./div/div[2]/div/ul/li/a/@title')),
                # text()表示獲取節(jié)點(diǎn)i里面的文本信息
                'price': _.xpath('./div/div[3]/strong/i/text()')[0],
                'info': ''.join(
                        _.xpath('./div/div[4]/a/em/text()')).strip(),
                'province': _.xpath('./div/div[9]/@data-province')[0]}
            print(infoResult)
    else:
        raise Exception("Failed to get page information, please check！")
    
    return None


if __name__ == '__main__':
    parsing()