python 爬虫笔记（二）

最新推荐文章于 2025-08-11 22:22:04 发布

原创最新推荐文章于 2025-08-11 22:22:04 发布 · 502 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #爬虫 #utf-8

抓取一个页面 id为giftList 的 table，的所有子节点

! /usr/bin/env python

coding=utf-8

import urllib2
from    bs4 import  BeautifulSoup

html=urllib2.urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj=BeautifulSoup(html)

for child in bsObj.find("table",{"id":"giftList"}).children:
            print(child)

#! /usr/bin/env python
#coding=utf-8

import urllib2
from    bs4 import  BeautifulSoup

html=urllib2.urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj=BeautifulSoup(html)

for siblings in bsObj.find("table",{"id":"giftList"}).tr.next_siblings:
            print(siblings)

#! /usr/bin/env python
#coding=utf-8

import urllib2
from    bs4 import  BeautifulSoup

html=urllib2.urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj=BeautifulSoup(html)

print(bsObj.find("img",{"src":"../img/gifts/img1.jpg"}).parent.previous_sibling.get_text())