运行代码时出现 'module' object has no attribute 'HtmlParser'报错
代码和老师的一样 出现这个报错
Traceback (most recent call last):
File "/home/桌面/python/baike_spider/spider_main.py", line 35, in <module>
obj_spider = SpiderMain()
File "/home/桌面/python/baike_spider/spider_main.py", line 10, in __init__
self.parser = html_parser.HtmlParser()
AttributeError: 'module' object has no attribute 'HtmlParser'
附上主程序代码
import html_downloader, html_outputer, html_parser, url_manager
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, rot_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.downloader(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 = " http://baike.baidu.com/view/21087.htm"
obj_spider = SpiderMain()
obj_spider.craw(root_url)