报错could not be imported, invalid character,求解非常感谢!
# -*- coding: utf-8 -*-
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'].encode())
fout.write('<td>%s</td>'%data['title'].encode())
fout.write('<td>%s</td>'%data['summary'].encode())
fout.write('</tr>')
fout.write('</table>')
fout.write('</body>')
fout.write('</html>')
fout.close()============================= ERRORS =============================
Traceback (most recent call last):
File "C:\Users\Administrator\.p2\pool\plugins\org.python.pydev.core_6.3.3.201805051638\pysrc\_pydev_runfiles\pydev_runfiles.py", line 468, in __get_module_from_str
mod = __import__(modname)
File "D:\practice\mooc\src\baike_spider\spider_main.py", line 23
if count == 1000:
  ^
SyntaxError: invalid character in identifier
ERROR: Module: spider_main could not be imported (file: D:/practice/mooc/src/baike_spider/spider_main.py).
# -*- coding: utf-8 -*-
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'].encode())
fout.write('<td>%s</td>'%data['title'].encode())
fout.write('<td>%s</td>'%data['summary'].encode())
fout.write('</tr>')
fout.write('</table>')
fout.write('</body>')
fout.write('</html>')
fout.close()============================= ERRORS =============================
Traceback (most recent call last):
File "C:\Users\Administrator\.p2\pool\plugins\org.python.pydev.core_6.3.3.201805051638\pysrc\_pydev_runfiles\pydev_runfiles.py", line 468, in __get_module_from_str
mod = __import__(modname)
File "D:\practice\mooc\src\baike_spider\html_parser.py", line 25
title_node = soup.find('dd', class="lemmaWgt-lemmaTitle-title").find('h1')
^
SyntaxError: invalid syntax
ERROR: Module: html_parser could not be imported (file: D:/practice/mooc/src/baike_spider/html_parser.py).
# -*- coding: utf-8 -*-
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'].encode())
fout.write('<td>%s</td>'%data['title'].encode())
fout.write('<td>%s</td>'%data['summary'].encode())
fout.write('</tr>')
fout.write('</table>')
fout.write('</body>')
fout.write('</html>')
fout.close()============================= ERRORS =============================
Traceback (most recent call last):
File "C:\Users\Administrator\.p2\pool\plugins\org.python.pydev.core_6.3.3.201805051638\pysrc\_pydev_runfiles\pydev_runfiles.py", line 468, in __get_module_from_str
mod = __import__(modname)
File "D:\practice\mooc\src\baike_spider\html_outputer.py", line 8
if data == None:
^
SyntaxError: invalid character in identifier
ERROR: Module: html_outputer could not be imported (file: D:/practice/mooc/src/baike_spider/html_outputer.py).