#Spider main
from baike_spider import url_manager, html_downloader
import html_parser
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+=1
except:
print'craw failed'
self.outputer.output_html()
def __init__(self):
self.new_urls = set()
self.old_urls = set()
if __name__=="__main__":
root_url="https://baike.baidu.com/item/Python/407313?fr=aladdin"
obj_spider=SpiderMain()
obj_spider.craw(root_url)
#outputer
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>')
for data in self.datas:
fout.write('<tr>')
fout.write('<td>%s</td>'% data['url'])
fout.write('<td>%s</td>'% data['title'])
fout.write('<td>%s</td>'% data['summary'])
fout.write('</tr>')
fout.write('</table>')
fout.write('</body>')
fout.write('</html>')
fout.close
