coinmarketcap.com爬虫

coinmarketcap.com爬虫

写的真是蛋疼

# -*- coding:utf-8 -*-

import requests
from lxml import etree

headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}

def get_tag():
    html = requests.get("https://coinmarketcap.com/zh/rankings/exchanges/",headers=headers).text
    keys = etree.HTML(html)
    keyss = keys.xpath("//td[@class='no-wrap currency-name']/@data-sort")
    for i in keyss:
        url = "https://coinmarketcap.com/zh/exchanges/"+i
        get_url(url)
def get_url(url):
    html = requests.get(url, headers=headers).text
    keys = etree.HTML(html)
    keyss = keys.xpath("//div[@class='col-xs-12']/ul[@class='list-unstyled']/li/a/@href")
    for i in keyss:
        print i
        break

if __name__ == '__main__':
    get_tag()