爬取网页文本

#!/bin/env python
# -*- coding: utf-8 -*-
import sys
import os
import requests
from lxml import etree
sys.path.append(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))



text = []
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36'}
target='https://ec.europa.eu/info/funding-tenders/procedures-guidelines-tenders/information-contractors-and-beneficiaries/exchange-rate-inforeuro_en'
get = requests.get(target,headers = headers,timeout=30)  # get(url) 得到我们的网页, text将源网页转化为字符串
get.encoding = "utf-8"#定义数据格式,避免乱码

get=get.text
selector = etree.HTML(get)  # 将源码转换为xpath可以识别的TML格式
info=selector.xpath('//select[@ng-model="fromCurrency"]/option//text()')
print(info)