使用爬虫对植物定种

代码

# -*- coding: UTF-8 -*-
import urllib
import urllib2
import re
name = str(raw_input('请输入物种名:'))
values={}
values['id'] = name
data = urllib.urlencode(values)
url = "http://frps.iplant.cn/frps"
geturl = url + "?"+data
request = urllib2.Request(geturl)
response = urllib2.urlopen(request)
content = response.read()
if "响应时间" in content:
    pattern = re.compile('24px.*?b>.*?\. (.*?)<', re.S)
    species = re.findall(pattern, content)
    species = species[0].replace('　', ',').replace('，', ',')
    pattern = re.compile('16px.*?Arial.*?b>(.*?)<.*?<b>(.*?)</b>', re.S)
    name = re.findall(pattern, content)
    name = " ".join(name[0])
    pattern = re.compile('<div.*?rightcon">(.*?)</div>', re.S)
    content = re.findall(pattern, content)
    # ?:的意思是不会作为子模式被查找
    pattern = re.compile('<span.*?>(.*?(?:门|纲).*?)<', re.S)
    # pattern = re.compile('<span.*?>([^<]*)<', re.S)
    items = re.findall(pattern, content[0])
    pattern = re.compile('<span.*?<a.*?>(.*?)</a', re.S)
    items += re.findall(pattern, content[0])
    items.append(species+" "+name)
    for item in items:
        print item
else:
    url = "https://zh.wikipedia.org/wiki/"
    geturl = url+data
    request = urllib2.Request(geturl)
    response = urllib2.urlopen(request)
    content = response.read()
    print content

原始页面

查询效果