python抓取网页数据的三种方法

import  re

import  urllib2

urllist  = 'example.webscraping.com/places/defa…'

html =  urllib2.urlopen(urllist).read()

num =  re.findall('<td class="w2p_fw">(.*?)</td>',html)

print  num

print  "num[1]: ",num[1]

from  bs4 import BeautifulSoup

import  urllib2

urllist  = 'example.webscraping.com/places/defa…'

html =  urllib2.urlopen(urllist).read()

#把html 格式进行确定和纠正

soup =  BeautifulSoup(html,'html.parser')

#找出tr 标签中id属性为places_area__row 的内容，如果把find改成findall 函数则会把匹配所#有的内容显示出来， find函数只匹配第一次匹配的内容。

tr =  soup.find('tr',attrs={'id':'places_area__row'})

td =  tr.find('td',attrs={'class':'w2p_fw'})

#取出标签内容

area =  td.text

print  "area: ",area

import  lxml.html

import  urllib2

urllist  = 'example.webscraping.com/places/defa…

w/United-Kingdom-239'

html =  urllib2.urlopen(urllist).read()

tree =  lxml.html.fromstring(html)

td =  tree.cssselect('tr#places_area__row > td.w2p_fw')[0]

area =  td.text_content()

print  area