获取当前页面的所有链接的四种方法对比(python 爬虫)
''' 得到当前页面所有连接 ''' import requests import re from bs4 import BeautifulSoup from lxml import etree from selenium import webdriver url = 'http://www.ok226.com' r = requests.get(url) r.encoding = 'gb2312' # 利用 re (太黄太暴力!) matchs = re.findall(r"(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')" , r.text) for link in matchs: print(link) print() # 利用 BeautifulSoup4 (DOM树) soup = BeautifulSoup(r.text,'lxml') for a in soup.find_all('a'): link = a['href'] print(link) print() # 利用 lxml.etree (XPath) tree = etree.HTML(r.text) for link in tree.xpath("//@href"): print(link) print() # 利用selenium(要开浏览器!) driver = webdriver.Firefox() driver.get(url) for link in driver.find_elements_by_tag_name("a"): print(link.get_attribute("href")) driver.close()
注意:若页面中含有 iframe,则 iframe 内所包含页面的所有标签都无法用以上四种方法获得!!!此时则要:
# 再打开所有iframe查找全部的a标签 for iframe in soup.find_all('iframe'): url_ifr = iframe['src'] # 取得当前iframe的src属性值
rr = requests.get(url_ifr) rr.encoding = 'gb2312'
soup_ifr = BeautifulSoup(rr.text,'lxml')
for a in soup_ifr.find_all('a'): link = a['href'] m = re.match(r'http:\/\/.*?(?=\/)',link) #print(link) if m: all_urls.add(m.group(0))