运行没有报错，但结果为空：
C:\Users\CCF\PycharmProjects\untitled\venv\Scripts\python.exe C:/Users/CCF/PycharmProjects/untitled/baike_spider/spider_main.py
Process finished with exit code 0
SpiderMain
# -*- coding: utf-8 -*-
from baike_spider import url_manager
from baike_spider import html_downloader
from baike_spider import html_parser
from baike_spider import html_outputer
class SpiderMain(object):
def _init_(self):
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('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)
if count == 1000:
break
count = count + 1
except:
print('craw failed')
self.outputer.output_html()
if __name__ == "_main_":
root_url = "https://baike.baidu.com/item/Python/407313"
obj_spider = SpiderMain()
obj_spider.craw(root_url)
url_manager
# -*- coding: utf-8 -*-
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
html_downloader
# -*- coding: utf-8 -*-
from urllib import request
class HtmlDownloader(object):
@staticmethod
def download(url):
if url is None:
return None
response = request.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
html_parser
# -*- coding: utf-8 -*-
import re
from bs4 import BeautifulSoup
from urllib import parse
class HtmlParser(object):
@staticmethod
def _get_new_urls(page_url, soup):
new_urls = set()
#https://baike.baidu.com/item/Python/407313
# /item/Google/86964
links = soup.find_all('a', href=re.compile(r"/item/"))
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 parse(self, page_url, html_cont):
# noinspection PyUnreachableCode
if page_url is None or html_cont is None:
return
# noinspection PyUnreachableCode
soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
new_urls = self._get_new_urls(page_url, soup)
new_data = _get_new_data(page_url, soup)
return new_urls, new_data
def _get_new_data( page_url, soup):
res_data = {'url': page_url}
#url
#<dd class="lemmaWgt-lemmaTitle-title"> <h1>Python</h1>
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
html_outputer
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
class HtmlOutputer(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("<body>")
fout.write("<table>")
# ASCII --> utf-8
for data in self.datas:
fout.write("<tr>")
fout.write("<td>%s</td>" % data['url'])
fout.write("<td>%s</td>" % data['title'].encode('utf-8'))
fout.write("<td>%s</td>" % data['summary'].encode('utf-8'))
fout.write("</tr>")
fout.write("</html>")
fout.write("</body>")
fout.write("</table>")
fout.close()
