使用的是python2.7
#主函数spider_main.py
# coding :utf8
from baike_spider import url_manager,html_downloader,html_outputer,\
html_parser
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?fr=aladdin"
obj_spider = SpiderMain( )
obj_spider.craw(root_url)
#url_manager.py
# coding : utf8
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_parser.py
# coding : utf8
import re
import urlparse
from bs4 import BeautifulSoup
class HtmlParser (object):
def _get_new_urls(self,page_url,soup):
new_urls = set ()
#/item/Python/407313?fr=aladdin
links = soup.find_all('a',href=re.compile(r"/item/Python/\d+\?fr=aladdin"))
for link in links:
new_url = link['href']
new_full_url = urlparse.urljoin(page_url,new_url)
new_urls.add(new_full_url)
return new_urls
def _get_new_date(self,page_url,soup):
res_date={}
# url
res_date['url'] =page_url
#<dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")
res_date['title'] = title_node.get_text()
#<div class="lemma-summary" label-module="lemmaSummary">
summary_node = soup.find('div',class_="lemma-summary")
res_date['summary'] = summary_node.get_text()
return res_date
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
import re
import urlparse
from bs4 import BeautifulSoup
class HtmlParser (object):
def _get_new_urls(self,page_url,soup):
new_urls = set ()
#/item/Python/407313?fr=aladdin
links = soup.find_all('a',href=re.compile(r"/item/Python/\d+\?fr=aladdin"))
for link in links:
new_url = link['href']
new_full_url = urlparse.urljoin(page_url,new_url)
new_urls.add(new_full_url)
return new_urls
def _get_new_date(self,page_url,soup):
res_date={}
# url
res_date['url'] =page_url
#<dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")
res_date['title'] = title_node.get_text()
#<div class="lemma-summary" label-module="lemmaSummary">
summary_node = soup.find('div',class_="lemma-summary")
res_date['summary'] = summary_node.get_text()
return res_date
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_downloader.py
# coding : utf8
import urllib2
class HtmlDownloader (object):
def download(self,url):
if url is None :
return None
response=urllib2.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
添加回答
举报
0/150
提交
取消