def test():
ext = CXExtractor()
urls = [
'http://baike.baidu.com/view/25215.htm',
'http://tieba.baidu.com/p/3069273254',
'http://hi.baidu.com/handylee/blog/item/6523c4fc35a235fffc037fc5.html',
'http://xiezuoshi.baijia.baidu.com/article/15330',
'http://www.techweb.com.cn/news/2010-08-11/659082.shtml',
'http://www.ifanr.com/15876',
'http://news.cnhubei.com/xw/yl/201404/t2894467_5.shtml',
]
import sys
sys.path.append('../py-crawler')
from spider_urllib2 import UrlSpider
spider = UrlSpider()
for url in urls:
raw_html, err = spider.download(url)
if raw_html:
print 'url:', url
start_time = time.time()
for i in xrange(0, 10):
title, content, keywords, desc= ext.extract(raw_html)
end_time = time.time()
print 'QPS:', 10/ (end_time-start_time)
print 'title:', title
print 'content:', content
else:
print 'url:', url
print 'error_msg:', err
def test_file(p_in):
ext = CXExtractor()
import sys
sys.path.append('../py-crawler')
from spider_urllib2 import UrlSpider
spider = UrlSpider()
for url in open(p_in):
url = url.strip()
if not url: continue
raw_html, err = spider.download(url)
if raw_html:
print '\nurl:', url
title, content, keywords, desc = ext.extract(raw_html)
print 'title:', title
print 'content:', content