本人使用的的sublime text 3,环境python 2.7.11 windows 7 x64
import url_manager,html_downloader,html_parser,\
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()
html_cont = self.downloader.download(new_url)
print 'craw %d: %s'%(count,new_url)
new_url,new_data = self.parser.parser(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.outputer_html()
if __name__=="__main__":
root_url = "http://baike.baidu.com/view/21087.htm"
obj_spider = SpiderMain()
obj_spider.craw(root_url)
报错信息:
Traceback (most recent call last):
File "F:\pytest\spider\spider_main.py", line 34, in <module>
obj_spider.craw(root_url)
File "F:\pytest\spider\spider_main.py", line 12, in craw
self.urls.add_new_url(root_url)
TypeError: add_new_url() takes exactly 1 argument (2 given)
[Finished in 0.4s with exit code 1]
[shell_cmd: python -u "F:\pytest\spider\spider_main.py"]
[dir: F:\pytest\spider]
清波
相关分类