python精简版搜索引擎

下面是脚本之家 jb51.cc 通过网络收集整理的代码片段。

脚本之家小编现在分享给大家，也给大家做个参考。

from html.parser import HTMLParser  
from urllib.request import urlopen  
from urllib import parse
class LinkParser(HTMLParser):

    def handle_starttag(self,tag,attrs):
        if tag == 'a':
            for (key,value) in attrs:
                if key == 'href':

                    newUrl = parse.urljoin(self.baseUrl,value)
                    self.links = self.links + [newUrl]

    def getLinks(self,url):
        self.links = []
        self.baseUrl = url
        response = urlopen(url)
        if response.getheader('Content-Type')=='text/html; charset=UTF-8':
            htmlBytes = response.read()
            htmlString = htmlBytes.decode("utf-8")
            self.feed(htmlString)
            return htmlString,self.links
        else:
            return "",[]

def spider(url,word,maxPages):  
    pagesToVisit = [url]
    numberVisited = 0
    foundWord = 4
    while numberVisited < maxPages and pagesToVisit != [] and not foundWord:
        numberVisited = numberVisited +1
        url = pagesToVisit[0]
        pagesToVisit = pagesToVisit[1:]
        try:
            print(numberVisited,"搜索页:",url)
            parser = LinkParser()
            data,links = parser.getLinks(url)
            #print("data:",links)
            pagesToVisit = pagesToVisit + links
            if data.find(word)>-1:
                foundWord = True
                pagesToVisit = pagesToVisit + links
                print(" **成功!**")
        except:
            print(" **错误!**")
    if foundWord:
        print("该关键字","搜索失败",url)
    else:
        print("没有找到任何有关的网页")
spider("http://yuedu.fm/","夏洛特",100)

以上是脚本之家(jb51.cc)为你收集整理的全部代码内容，希望文章能够帮你解决所遇到的程序开发问题。

如果觉得脚本之家网站内容还不错，欢迎将脚本之家网站推荐给程序员好友。

（编辑：安卓应用网）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!