爬虫（二）

!/usr/bin/env python
-*- encoding:UTF-8 -*-

import requests

headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36‘
}
res = requests.get(‘http://bj.xiaozhu.com/‘,headers=headers)    # get方法加入请求头
try:
    print(res.text)
except ConnectionError:
    print(‘拒绝连接‘)


# 通过BeautiSoup库解析得到的Soup文档是标准结构化数据比上面的更好
import requests
from bs4 import BeautifulSoup

headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36‘
}
res = requests.get(‘http://bj.xiaozhu.com/‘,headers=headers)    # get方法加入请求头
try:
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    print(soup.prettify())
except ConnectionError:
    print(‘拒绝连接‘)

price = soup.select(‘#page_list > ul > li:nth-child(1) > div.result_btm_con.lodgeunitname > div:nth-child(1) > ‘
                    ‘span.result_price > i‘)