极客观点
项目管理
HarmonyOS
代码如下：
spider_main.py:
# coding:utf8
import html_outputer, html_downloader, url_manager,\
html_parser
class SpiderMain(object):
def __init__(self):
self.urls=url_manager.UrlManager()
self.downloader=html_downloader.HtmlDownloader()
self.parser=html_parser.HtmlParse()
# self.outputer=html_outputer.HtmlOutputer()
self.html_outputer = html_outputer.Html0utputer()
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("craw %d :%s"%(count,new_url))
html_cont=self.downloader.download(new_url)
new_urls,new_data=self.parser.parse(new_url,html_cont)
self.urls.add_new_urls(new_urls)
# self.outputer.collect_data(new_data)
self.html_outputer.collect_data(new_data)
if count==1000:
break
count=count+1
except:
print("craw failed")
# self.outputer.output_html()
self.html_outputer.output_html()
if __name__=="__main__":
root_url="http://baike.baidu.com/view/21087.htm"
obj_spider=SpiderMain()
obj_spider.craw(root_url)
html_downloader.py:
Created on 2017-7-3
@author: Administrator
'''
import 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()
html_parser.py
# coding:utf-8
from bs4 import BeautifulSoup
import re
from urllib import parse
class HtmlParse(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']
new_full_url = parse.urljoin(page_url, new_url)
new_urls.add(new_full_url)
return new_urls
def _get_new_data(self, page_url, soup):
# <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
res_data = {}
# url\
res_data['url'] = page_url
title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find("h1")
res_data['title'] = title_node.get_text()
# <div class="lemma-summary" label-module="lemmaSummary">
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')
new_urls = self._get_new_urls(page_url, soup)
new_data = self._get_new_data(page_url, soup)
return new_urls, new_data
html_outputer.py:
# coding:utf8
class Html0utputer(object):
def __init__(self):
self.datas = []
def collect_data(self,data):
if data is None:
return
self.datas.append(data)
def output_html(self):
fout = open('output.html', 'w')
fout.write('<html>')
fout.write("<head><meta http-equiv='content-type' content='text/html;charset=utf-8'></head>")
fout.write('<body>')
fout.write('<table>')
# ascci
for data in self.datas:
fout.write('<tr>')
fout.write('<td>%s</td>' % data['url'])
fout.write('<td>%s</td>' % data['title'].encode(encoding='UTF-8'))
fout.write('<td>%s</td>' % data['summary'].encode(encoding='UTF-8'))
fout.write('</tr>')
fout.write('</table>')
fout.write('</body>')
fout.write('</html>')
url_manager.py:
'''
Created on 2017-7-3
@author: Administrator
'''
class UrlManager(object):
def __init__(self):
self.new_urls = set()
self.old_urls = set()
def add_new_url(self, url):# 第一个方法：向管理器中添加一个URL
# 添加判断
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):# 添加批量URL
if urls is None or len(urls) == 0:
return
for url in urls:
self.add_new_url(url)
def has_new_url(self):# 看是否有待爬取的URL
return len(self.new_urls) != 0
def get_new_url(self):#
# pop()方法从列表中获取URL，同时移除URL
# 首先添加进URL
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
但是我运行spider_main.py结果如下：
正确结果应该是这样的：
请问这是什么原因？
python
HtmlOutputer::output_html: