我的代码是用pycharm敲的，为啥到运行的时候报了这个错，求大神解答，谢谢
我感觉没啥错啊，都是对着老师的代码敲得，哭泣
4 回答
# 载入url管理器，解析器，下载器，输出器模块
from SpiderBaike import url_manager, html_parser, html_downloader, html_output
# 定义爬虫类
class Spider(object):
def __init__(self):
# url管理器类等生成实例对象
self.url_manager = url_manager.UrlManager()
self.parser = html_parser.Parser()
self.downloader = html_downloader.Downloader()
self.output = html_output.Output()
def crawl(self, root_url):
count = 1
self.url_manager.add(root_url)
while self.url_manager.has_new():
try:
new_url = self.url_manager.get_url()
print(count)
print(new_url)
html_cont = self.downloader.download(new_url)
new_urls, data = self.parser.parse(new_url, html_cont)
self.output.get_data(data)
self.url_manager.add_list(new_urls)
if count == 10:
break
count = count + 1
except:
print('Craw failed')
if __name__ == '__main__':
root_url = 'https://baike.baidu.com/item/Python'
obj_spider = Spider()
obj_spider.crawl(root_url)发现自己哪里错了，错把__init__ 写成了 __int__了，楼主你应该和我的问题差不多，看看你的__init__方法吧
# 载入url管理器，解析器，下载器，输出器模块
from SpiderBaike import url_manager, html_parser, html_downloader, html_output
# 定义爬虫类
class Spider(object):
def __int__(self):
# url管理器类等生成实例对象
self.m_url_manager = url_manager.UrlManager()
self.m_parser = html_parser.Parser()
self.m_downloader = html_downloader.Downloader()
self.m_output = html_output.Output()
def crawl(self, root_url):
print(root_url)
# count = 1
self.m_url_manager.add(root_url)
# while self.m_url_manager.has_new():
# try:
# new_url = self.m_url_manager.get_url()
# print(count)
# print(new_url)
# html_cont = self.m_downloader.download(new_url)
# new_urls, data = self.m_parser.parse(new_url, html_cont)
# self.m_output.get_data(data)
# self.m_url_manager.add_list(new_urls)
# if count == 10:
# break
# count = count + 1
# except:
# print('Craw failed')
if __name__ == '__main__':
root_url = 'https://baike.baidu.com/item/Python'
obj_spider = Spider()
obj_spider.crawl(root_url)我的和你一样报错，怎么解决？
举报
0/150
提交
取消
