1:运行环境:
python: 3.7.0
系统:Windows
IDE:pycharm 2017
2:需要安装的库:
requests 和 beautifulsoup
3:完整代码:
# coding:utf-8
import requests
from bs4 import BeautifulSoup
import bs4
def gethtml(url,headers):
response = requests.get(url,headers=headers)
try:
if response.status_code == 200:
print('抓取成功网页长度:',len(response.text))
response.encoding = 'utf-8'
return response.text
except BaseException as e:
print('抓取出现错误:',e)
def getsoup(html):
soup = BeautifulSoup(html,'lxml')
for tr in soup.find('tbody').children: #生成tr的tag列表
if isinstance(tr,bs4.element.Tag):
td = tr('td') #循环获取所有tr标签下的td标签,并生成tag列表
t = [td[0].string, td[1].string,' ',td[2].string,' ',td[3].string] #提取前四td字符串