Python获取当前页面内的所有链接的五种方法

本文讲述了 Python 获取当前页面内的所有链接的五种方法,分享给大家仅供参考,具体如下:

# 利用 requests_html
from requests_html import HTMLSession
session &＃61; HTMLSession()
url &＃61; &＃39;https://www.baidu.com&＃39;
r &＃61; session.get(url)
print(r.html.links)
print(&＃39;*&＃39;*100)
# 利用 BeautifulSoup
import requests
from bs4 import BeautifulSoup
url &＃61; &＃39;http://www.baidu.com&＃39;
res &＃61; requests.get(url)
soup &＃61; BeautifulSoup(res.text, &＃39;lxml&＃39;)
for a in soup.find_all(&＃39;a&＃39;):
print(a[&＃39;href&＃39;])
print(&＃39;*&＃39;*100)
# 利用 re (不推荐用正则,太麻烦)
# 利用 lxml.etree
from lxml import etree
tree &＃61; etree.HTML(r.text)
for link in tree.xpath(&＃39;//&＃64;href&＃39;):
print(link)
print(&＃39;*&＃39;*100)
# 利用 selenium
from selenium import webdriver
chrome_options &＃61; webdriver.ChromeOptions()
chrome_options.add_argument(&＃39;--headless&＃39;)
browser &＃61; webdriver.Chrome(chrome_options&＃61;chrome_options)
browser.get(url)
for link in browser.find_elements_by_tag_name(&＃39;a&＃39;):
print(link.get_attribute(&＃39;href&＃39;))