pyth 数据采集

数据采集

=============

beautifulsoup4文档：

https://www.crummy.com/software/BeautifulSoup/bs4/doc/

安装beautifulsoup4

https://www.crummy.com/software/BeautifulSoup/
pip install beautifulsoup4
from bs4 import BeautifulSoup

===================
 from urllib.request import urlopen
 C:\Users\ljf>pip install beautifulsoup4    //安装 bs4
 from bs4 import BeautifulSoup
PyDev - http://pydev.org/nightly
http://www.ibm.com/developerworks/cn/opensource/os-cn-ecl-pydev/

1

import  urllib.request
#print (urllib.request)
class HtmlDownloader(object):


    def download(self,url):
        if url is None:
            return None


        response = urllib.request.urlopen(url)    


        if response.getcode() != 200:
            return None
        return response.read()
#obj = HtmlDownloader()
#obj.download("http://baike.bai du.com/view/21087.htm")

2

from  bs4 import BeautifulSoup
import re
#import urlparse
#import urllib.request


class HtmlParser(object):


    def _get_new_urls(self,page_url,soup):
        new_urls = set()
        links = soup.find_all("a",href=re.compile(r"/view/\d+\.htm"))
        for link in links:
            new_url = link['href']
#            print(new_url)
            new_full_url = "http://baike.baidu.com"+new_url
#            print (new_full_url)
            new_urls.add(new_full_url)


        return new_urls


    def _get_new_data(self,page_url,soup):
            res_data = {}
            res_data['url'] = page_url
            ttile_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")


            res_data['title'] = ttile_node.get_text()


            summary_node = soup.find("div",class_="lemma-summary")
            res_data['summary'] = summary_node.get_text()
            return res_data


    def parse(self,page_url,html_cont):
        if page_url is None or html_cont is None:
            return


        soup = BeautifulSoup(html_cont,'html.parser',from_encoding = "utf-8")
#        print (soup)
        new_urls = self._get_new_urls(page_url,soup)
#        print (new_urls)
        new_data = self._get_new_data(page_url,soup)
        return new_urls, new_data


#test = HtmlParser()
#response = urllib.request.urlopen("http://baike.baidu.com/view/21087.htm")
#test.parse("http://baike.baidu.com/view/21087.htm",response.read())

3

import  sys
import os
curPath = os.path.abspath(os.path.dirname(__file__))
rootPath = os.path.split(curPath)[0]
sys.path.append(rootPath)
from baike_spider import url_manager,html_downloader, html_parser,html_outputer


class SpiderMain(object):
    def __init__(self):
        print ('22222222222')
        # url 管理器， 模板下载器，下载数据解析器，解析数据输入器。 模块调度器
        self.urls = url_manager.UrlManager()   
        self.downloader = html_downloader.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_outputer.HtmlOutputer()




    def craw(self,root_url):    
        count = 1
        self.urls.add_new_url(root_url)


        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print (count,new_url)
#                print craw (‘ %d : %s‘) % (count,new_url)
                html_cont = self.downloader.download(new_url)
                new_urls,new_data = self.parser.parse(new_url,html_cont)
                print (new_urls)
                print (new_data)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)
                if count == 10:
                    break


                count = count + 1


            except:
                print ('craw fail')
                        
        self.outputer.output_html()    




if __name__ =="__main__":
    print ('1111111111111')
    root_url = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)      

4 

class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()


    def add_new_url(self,url):
        if url is None:
            return
        if url not in self.new_urls and url not in self.old_urls:
            self.new_urls.add(url)


    def add_new_urls(self,urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(url)


    def has_new_url(self):
        return len(self.new_urls) != 0


    def get_new_url(self):
        new_url =  self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

5