用Python获取网站数据

Question

这是我的代码，但是我的正则表达式还是有问题，求解

#coding=utf-8
import urllib2;
import re;
def getProvince(mainUrl):
    req = urllib2.Request(mainUrl);
    resp = urllib2.urlopen(req);
    respHtml = resp.read();
    # print "respHtml",respHtml;
    #<a href="/lelist/listxian.aspx?id=D44C1502B7D5BEA1" class="cunpaddingl4">安徽</a>
    #re.search('<h1\s+?class="h1user">(?P<h1user>.+?)</h1>', respHtml);
    foundA_lable = re.search('<a\s+?class=cunpaddingl4>(?P<cunpaddingl4>.+?)</a>',respHtml);
    print "foundA_lable =",foundA_lable;
    if foundA_lable:
        province = foundA_lable.group("cunpaddingl4");
        print u"cunpaddingl4 =",province;
    else :
        print u"没有匹配到数据";
        
print getProvince("http://www.yigecun.com/");

Answer 1

稍微改了一下你的代码，主要是改为用re.findall()，返回一个list，然后循环遍历打印。
用bs4也方便实现。

#coding=utf-8
import urllib2
import re

def getProvince(mainUrl):
    req = urllib2.Request(mainUrl)
    resp = urllib2.urlopen(req)
    respHtml = resp.read()
    # print "respHtml",respHtml;
    #<a href="/lelist/listxian.aspx?id=D44C1502B7D5BEA1" class="cunpaddingl4">安徽</a>
    #re.search('<h1\s+?class="h1user">(?P<h1user>.+?)</h1>', respHtml);
    foundA_lable = re.findall('<a\s+\S+\s+class="cunpaddingl4">(?P<cunpaddingl4>.+?)</a>', respHtml)
    print "foundA_lable =", len(foundA_lable)
    for province in foundA_lable:
        # province = foundA_lable.group("cunpaddingl4")
        print u"cunpaddingl4 =", province
        
getProvince("http://www.yigecun.com/")