Python 爬虫入门二(标签)

 通过标签及样式名获取

# coding=UTF-8
from urllib2 import urlopen, HTTPError
from bs4 import BeautifulSoup


def getName(url):
    try:
        html = urlopen(url)
    except HTTPError as e:
        return e

    try:
        bs = BeautifulSoup(html.read(), 'html.parser')
        nameList = bs.findAll('span', {'class': 'green'})
        for name in nameList:
            print (name.get_text())                  #get_text()获取标签里的类容
    except AttributeError as e:
        return e


if __name__ == '__main__':
    title = getName('网页URL')

---

获取指定子标签(打印表格所有的子标签内容)

def getChildren():
    html = urlopen('网页URL')
    bs = BeautifulSoup(html, 'html.parser')
    for child in bs.find('table' , {'id':'list'}).children:
        print (child)

---

获取兄弟标签(打印表格除第一行标题外的所有标签内容)

def getNext():
    html = urlopen('网页URL')
    bs = BeautifulSoup(htm