爬取网页后的抓取数据_3种抓取网页数据方法

    re.findall('<tr id="places_area__row">.*?<td\s*class=["\']w2p_fw["\']>(.*?)</td>', html)
    
    代码解读

 import re

    
 pattern = re.compile("hello")
    
 #match_list = re.findall(pattern, "hello world! hello") 这个是找全部匹配的，返回列表
    
 match = pattern.match("hello world! hello") #这个是找匹配的，有就返回一个，没有返回None
    
 print(match)
    
    
    
    
    代码解读

 from bs4 import BeautifulSoup

    
 >>> soup = BeautifulSoup(html, "html.parser")    #用html解释器对得到的html文本进行解析
    
 >>> tr = soup.find(attrs={"id":"places_area__row"})
    
 >>> tr
    
 <tr id="places_area__row"><td class="w2p_fl"><label for="places_area" id="places_area__label">Area: </label></td><td class="w2p_fw">244,820 square kilometres</td><td class="w2p_fc"></td></tr>
    
 >>> td = tr.find(attrs={"class":"w2p_fw"})
    
 >>> td
    
 <td class="w2p_fw">244,820 square kilometres</td>
    
 >>> area = td.text
    
 >>> print(area)
    
 244,820 square kilometres
    
    
    
    
    代码解读

 #先解析网页源码（lxml）示例

    
 import lxml.html
    
 broken_html = "<ul class=country><li>Area<li>Population</ul>"
    
 tree = lxml.html.fromstring(broken_html)  #解析已经完成
    
 fixed_html = lxml.html.tostring(tree, pretty_print=True)  
    
 print(fixed_html)
    
  
    
 #output
    
 #b'<ul class="country">\n<li>Area</li>\n<li>Population</li>\n</ul>\n'
    
    
    
    
    代码解读

 #解析网页源码（lxml）后使用css选择器提取目标信息

    
 import lxml.html
    
 import cssselect
    
 html = download("http://example.webscraping.com/view/Aland-Islands-2") #下载网页
    
 html = str(html)
    
 tree = lxml.html.fromstring(html)  #解析已经完成
    
 td = tree.cssselect("tr#places_area__row > td.w2p_fw")[0]  #选择id="plac..."名为tr的标签下的，class="w2p..."名为td的标签中[0]元素
    
 area = td.text_content()   #目标信息area值为td标签中的text信息
    
 print(area)
    
    
    
    
    代码解读