import pandas as pandas
import requests
from lxml import etree

URL = "https://www.yunpian.com/doc/zh_CN/domestic/list.html"


# 獲取資源
def get_resource(url):
    return requests.get(url).content.decode('utf-8')


# 解析資源
def analysis_resource(html_text):
    html = etree.HTML(html_text)
    ports = html.xpath('//*[@id="book-search-results"]/div[1]/section/table/tbody/tr/td[1]/a/text()')
    links = html.xpath('//*[@id="book-search-results"]/div[1]/section/table/tbody/tr/td[2]/code/text()')
    descs = html.xpath('//*[@id="book-search-results"]/div[1]/section/table/tbody/tr/td[3]/text()')
    return zip(ports, links, descs)


# 儲存資源
def save_resource(zip_resource):
    params = []
    for port, link, desc in zip_resource:
        param = {
            "port": port,
            "link": link,
            "desc": desc
        }
        params.append(param)
    df = pandas.DataFrame(params)
    df.to_excel("yun_pian_ports.xlsx")


# 走起
if __name__ == "__main__":
    html_text = get_resource(URL)
    zip_resource = analysis_resource(html_text)
    save_resource(zip_resource)