#request #lxml 爬虫

import pandas as pd
import requests
from lxml import html

# 获取用户代理
headers = {
    'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Mobile Safari/537.36'}
# 网址
url = 'http://localhost:6263/'
# 获取网页
responses = requests.get(url, headers=headers)
# 设置编码格式
responses.encoding = 'utf-8'
tree = html.fromstring(responses.text)
print(tree)
trs = tree.xpath('//*[@id="data-view"]/tbody/tr')
all_data = []
for tr in trs:
    tds = tr.xpath('.//td')
    row_data = []
    for td in tds:
        data = td.xpath('.//text()')[0].strip()
        row_data.append(data)
    all_data.append(row_data)

# trs = soup.find('tbody').find_all('tr', role="row")
# data_all = []
# for tr in trs:
#     data_row = []
#     tds = tr.find_all("td")
#     for td in tds:
#         data_row.append(td.text.strip())
#     data_all.append(data_row)
result = pd.DataFrame(all_data,columns = ["排名","姓名","财富","行业","财富来源"])
result.to_csv('./result/result.csv',index=False)