pp3zah5lx
f3bb7b00f9
|
6 months ago | |
|---|---|---|
| README.md | 6 months ago | |
| demo.py | 6 months ago | |
| 单元实践 使用BeautifulSoup解析网页.doc | 6 months ago | |
README.md
BeautifulSoup
import requests from bs4 import BeautifulSoup
#获取url def urlList(): url = "https://www.ncrczpw.com/index.php?m=jobfair&c=index&a=index" head = { 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0' } r = requests.get(url,headers=head) r.encoding = 'utf-8' bea = BeautifulSoup(r.text,'lxml') text = bea.select("div.td2 a") arr = [] for i in text: arr.append(i.get("href")) arr.pop() return arr
#获取前8个内容 def text(url): head = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0' } r = requests.get(url, headers=head) r.encoding = 'utf-8' bea = BeautifulSoup(r.text, 'lxml') sum = "" text = bea.select("div.jobfairshow div.txt") for i in text: # print(i.get_text(strip=True)) sum = sum + i.get_text(strip=True) + "," text = bea.select("div a strong") for i in text: # print(i.get_text(strip=True)) sum = sum + i.get_text(strip=True) + "," print(sum)
arr = urlList() print(arr) for i in range(0,8): text(arr[i])