python爬取菜价
就附个简单bs4使用
import requests
from bs4 import BeautifulSoup
url = "http://www.bjtzh.gov.cn/bjtz/home/jrcj/index.shtml"
resp = requests.get(url)
# 页面源代码交给BeautifulSoup进行处理,生成bs对象
resp.encoding = 'UTF-8' # 爬取网页先看是什么编码
page = BeautifulSoup(resp.text, "html.parser") # 指定HTML解析器
table = page.find("table", attrs={"width": "588"})
trs = table.find_all("tr")
for tr in trs:
try:
tds = tr.find_all("td")
name = tds[0].text
kind = tds[1].text
high = tds[2].text
avg = tds[3].text
except IndexError as e:
continue # 因为网站有些表格不规范,直接抛出错误
print(name, kind, high, avg)