def generateCourseBaseCode(self, course):
index = 0
if self.course_base_dict.__contains__(course.coursebase_name):
self.current_base_course = self.course_base_dict.get(
course.coursebase_name)
course.coursebase_code = self.current_base_course.coursebase_code
course.coursebase_index = self.current_base_course.coursebase_index
else:
if self.current_base_course is None:
index = 1
else:
index = self.current_base_course.coursebase_index
if self.max_index >= index:
self.max_index += 1
else:
self.max_index = index
course.coursebase_code = 'open.bc.' + str(self.max_index)
course.coursebase_index = self.max_index
# 课程基础
cb = CourseInfomation.CourseBase()
cb.coursebase_code = course.coursebase_code
cb.coursebase_name = course.coursebase_name
cb.coursebase_index = course.coursebase_index
self.course_base_dict[cb.coursebase_name] = cb
self.current_base_course = cb
def createCypherFile(self, course):
"""
数据生成cypher语句文件
:param course:
:return:
"""
if not self.exam_info.examquestion_dict.__contains__(course):
return
exam_question_list = self.exam_info.examquestion_dict.get(course)
# 将知识点和试题关联起来
cypherlist = self.generateCypher(course, exam_question_list)
# 保存数据
course_path_info = CourseInfomation.CourseFilepath()
course_path_info.courseware_source_directory = self.rootpath
course_path_info.initByCourse(course)
file_name = course_path_info.cypher_txt_filepath
fout = open(file_name, 'w')
for item in cypherlist:
fout.write(item)
fout.write('\n')
fout.close()
print 'cypher文件：{}已生成'.format(course.NewCourseName)
return cypherlist
def associateFlow(self, course_list):
"""
关联流程，按步骤执行即可
:return:
"""
self.treefactory.course_filepath_list = []
for course_tuple in course_list:
course_path_info = CourseInfomation.CourseFilepath()
# 指定课件的源文件路径
course_path_info.courseware_source_directory = self.srcrootpath
course_path_info.courseware_source_docx_filepath = self.c_rootpath + '/' + course_tuple[
1]
course_path_info.initByCourse(course_tuple[0])
self.treefactory.course_filepath_list.append(course_path_info)
print '正在转换docx到txt，并抽取知识树...'
self.treefactory.extractKnowledge()
#self.knowledgemidfilepath = self.treefactory.wordreader.outputmidfilepath
print '知识树抽取完成。'
# 第三步：处理试题源文件，生成训练和测试样本
print '开始获取试题数据...'
self.questionSourceFileProcess(self.treefactory.course_filepath_list)
#print '开始生成试题词网...'
#self.questionGenerateWordnet()
#print '试题数据获取、试题词网生成完成。'
print '试题数据获取完成。'
# 第四步：将知识点和试题进行关联
print '开始关联试题与知识点...'
self.questionAndKnowledge(self.treefactory.course_filepath_list)
print '完成试题与知识点的关联。'
def createCorpusFile(self, course_path_info):
# 将结果按文件id输出
course = course_path_info.course
if self.exam_info.examquestion_dict.__contains__(course):
file_name = course_path_info.examquestion_source_txt_filepath
row_list = self.exam_info.examquestion_dict.get(course)
fout = open(file_name, 'w')
for item in row_list:
fout.write(item.getContentAndAnswer())
fout.write('\n')
fout.close()
print '语料文件：{}已生成'.format(course.NewCourseName)
return
# 下面的是生成全集的
for course in self.exam_info.examquestion_dict.keys():
course_path_info = CourseInfomation.CourseFilepath()
course_path_info.courseware_source_directory = self.rootpath
course_path_info.initByCourse(course)
file_name = course_path_info.examquestion_source_txt_filepath
row_list = self.exam_info.examquestion_dict.get(course)
fout = open(file_name, 'w')
for item in row_list:
fout.write(item.getContentAndAnswer())
fout.write('\n')
fout.close()
print '语料文件：{}已生成'.format(course.NewCourseName)
def __init__(self, course_source_filename):
"""
initialize data
"""
# course对象
self.course_info = CourseInfomation.CourseDictionary(
course_source_filename)
self.excel_reader = ExcelReader.ExcelReader()
def statistics(self):
"""
对course_score_list中的结果，进行统计
:return:
"""
# 课程的数量分布统计变量
n_coure_count_more50 = 0
n_coure_score_less50 = 0
# 统计所有课程，百分比的分布情况
n_coure_score = CourseInfomation.CourseScore()
for course_score in self.course_score_list:
n_coure_score.score_scope_more60_count += course_score.score_scope_more60_count
n_coure_score.score_scope_between5060_count += course_score.score_scope_between5060_count
n_coure_score.score_scope_between4050_count += course_score.score_scope_between4050_count
n_coure_score.score_scope_less40_count += course_score.score_scope_less40_count
# 如果50分以上的超过50%，则more50+1
if (n_coure_score.score_scope_between5060_count +
n_coure_score.score_scope_more60_count):
n_coure_count_more50 += 1
else:
n_coure_score_less50 += 1
n_coure_score.compute()
ns = '试题总数：{}'.format(n_coure_score.score_scope_total)
print ns
ns = '比较靠谱数(60分以上)：{} ，比较靠谱占比：{}%'.format(
n_coure_score.score_scope_more60_count,
round(n_coure_score.score_scope_more60_rate * 100, 2))
print ns
ns = '基本靠谱数(50-60分)：{} ，基本靠谱占比：{}%'.format(
n_coure_score.score_scope_between5060_count,
round(n_coure_score.score_scope_between5060_rate * 100, 2))
print ns
ns = '不太靠谱数(40-50分)：{} ，不太靠谱占比：{}%'.format(
n_coure_score.score_scope_between4050_count,
round(n_coure_score.score_scope_between4050_rate * 100, 2))
print ns
ns = '不靠谱数(40分以下)：{} ，不靠谱占比：{}%'.format(
n_coure_score.score_scope_less40_count,
round(n_coure_score.score_scope_less40_rate * 100, 2))
print ns
# 统计课程所在区域的分布情况
n_coure_count_total = n_coure_score_less50 + n_coure_count_more50
n_coure_score_less_rate = float(
n_coure_score_less50) / n_coure_count_total
n_coure_count_more_rate = float(
n_coure_count_more50) / n_coure_count_total
ns = '50%以上的试题得分大于50分的课程数量：{} 占比：{}'.format(n_coure_count_more50,
n_coure_count_more_rate)
print ns
ns = '50%以上的试题得分小于50分的课程数量：{} 占比：{}'.format(n_coure_score_less50,
n_coure_score_less_rate)
print ns
pass
def loadBaseCourse(self, base_course_file):
if not FilePath.fileExist(base_course_file):
return
f_input = open(base_course_file, 'r')
for line in f_input:
line = line.strip('\n')
cb = CourseInfomation.CourseBase()
cb.initByString(line)
self.course_base_list.append(cb)
self.current_base_course = cb
def __init__(self):
"""
initialize local variables.
"""
self.courseinfo = CourseInfomation.CourseDictionary()
#self.courseinfo.initDictionary(u'./../data/dictionary/course.txt')
self.excelreader = ExcelReader.ExcelReader()
self.re_num_0 = ur'(第[一二三四五六七八九零十百千万亿0123456789]+[章节讲])'
self.pattern = re.compile(self.re_num_0)
self.outputfile = u'./../data/course-knowledge-tgt/'
def __init__(self, course_source_filename):
"""
initialize data
"""
# course对象
self.course_info = CourseInfomation.CourseDictionary(
course_source_filename)
self.excel_reader = ExcelReader.ExcelReader()
self.course_base_dict = {}
self.course_base_list = []
self.current_base_course = None
self.max_index = 0
def loadProcessedCourse(self, rootpath):
output_mid_filepath = '{}/statistics-mid.txt'.format(rootpath)
if not FilePath.fileExist(output_mid_filepath):
return
fout = open(output_mid_filepath, 'r')
lines = fout.readlines()
for one_course_str in lines:
course_score = CourseInfomation.CourseScore()
course_score.initByString(one_course_str)
key = '{}-{}'.format(course_score.school_code,
course_score.course_code)
self.course_processed_dict[key] = course_score
self.course_score_list.append(course_score)
fout.close()
def __init__(self):
"""
initialize data
"""
self.result = []
self.cypher = None
self.cypherlist = []
self.knowledge = {}
self.question = {}
self.course = CourseInfomation.CourseDictionary()
#self.course.initDictionary(u'./../data/dictionary/course.txt')
# 记录没有知识点的行，打印用
self.no_kwg_row_count = 0
# 初始化列
self.__initColumn()
def createExcelFile(self):
"""
按照课程，分别存储每个文件
:return:
"""
for course in self.exam_info.examquestion_dict.keys():
course_path_info = CourseInfomation.CourseFilepath()
course_path_info.courseware_source_directory = self.rootpath
course_path_info.initByCourse(course)
file_name = course_path_info.examquestion_source_xlsx_filepath
row_list = self.exam_info.examquestion_dict.get(course)
column_data_list = []
column_data_list.append(QuestionInformation.column_head_list)
for exam_question in row_list:
if exam_question.content.startswith(u'<img'):
continue
column_data_list.append(exam_question.toList())
sheet_datas = {}
sheet_datas['sheet1'] = column_data_list
ExcelWriter.writeExcelFile(
course_path_info.examquestion_source_xlsx_filepath,
sheet_datas)
print 'Excel文件：{}已生成'.format(course.NewCourseName)
def statistics(self, statistics_filepath):
"""
对course_score_list中的结果，进行统计
:return:
"""
# bad course list
bad_course_list = []
# 课程的数量分布统计变量
n_coure_count_more50 = 0
n_coure_score_less50 = 0
f_stat = open(statistics_filepath, 'w')
# 统计所有课程，百分比的分布情况
n_coure_score = CourseInfomation.CourseScore()
for course_score in self.course_score_list:
n_coure_score.score_scope_more60_count += course_score.score_scope_more60_count
n_coure_score.score_scope_between5060_count += course_score.score_scope_between5060_count
n_coure_score.score_scope_between4050_count += course_score.score_scope_between4050_count
n_coure_score.score_scope_less40_count += course_score.score_scope_less40_count
course_descrip = course_score.getDescription()
f_stat.write('\n'.join(course_descrip))
f_stat.write('\n\n')
# 如果50分以上的超过50%，则more50+1
if (course_score.score_scope_between5060_rate +
course_score.score_scope_more60_rate) > 0.5:
n_coure_count_more50 += 1
else:
n_coure_score_less50 += 1
bad_course_list.append(course_score)
f_stat.write('所有课程的汇总统计：')
course_descrip = n_coure_score.getDescription()
f_stat.write('\n'.join(course_descrip))
f_stat.write('\n\n')
# 统计课程所在区域的分布情况
n_coure_count_total = n_coure_score_less50 + n_coure_count_more50
if n_coure_count_total > 0:
n_coure_score_less_rate = float(
n_coure_score_less50) / n_coure_count_total
n_coure_count_more_rate = float(
n_coure_count_more50) / n_coure_count_total
ns = '50%以上的试题得分大于50分的课程数量：{} 占比：{}'.format(
n_coure_count_more50, n_coure_count_more_rate)
print ns
ns = '50%以上的试题得分小于50分的课程数量：{} 占比：{}'.format(
n_coure_score_less50, n_coure_score_less_rate)
print ns
# 保存bad course信息
print 'bad course information.'
for bad_course in bad_course_list:
course_descrip = bad_course.getDescription()
f_stat.write('\n'.join(course_descrip))
f_stat.write('\n')
# 保存未识别的课程
f_stat.write('\n\n')
f_stat.write('未识别的课程：')
f_stat.write('\n'.join(self.course_unrecongnized))
f_stat.write('\n\n')
f_stat.write('超出范围的课程：')
f_stat.write('\n'.join(self.course_over_scope))
f_stat.close()
answer_content = answer_content + ', ' + str(question_row[4])
if str(question_answer).__contains__('D'):
answer_content = answer_content + ', ' + str(question_row[5])
if str(question_answer).__contains__('E'):
answer_content = answer_content + ', ' + str(question_row[6])
answer_content = str(answer_content)
if len(answer_content):
answer_content = answer_content[1:]
knowledge = ''
if len(question_row) > 12:
knowledge = str(question_row[12])
content = '{}:: {} 答案：{}'.format(knowledge, question_content,
answer_content)
return content
if __name__ == '__main__':
#read_excel()
er = ExamQuestionProcessor()
er.isTest = True
course_path_info = CourseInfomation.CourseFilepath()
course_path_info.courseware_source_directory = er.rootpath
course_path_info.examquestion_source_xlsx_filepath = u'{}/q-xlsx/20181122-200plus.xlsx'.format(
er.rootpath)
course_info = CourseInfomation.CourseDictionary()
er.setCourseInfo(course_info)
er.courseExamQuestionGenerator(course_path_info)
print ''
def batchProcessAssociate1(self, dirname):
"""
批量处理多个课程的自动关联工作
:return:
"""
# 指定一个文件夹，该文件夹用来存放多个课程的pdf课件
# 逐个课件处理
# 首先指定根目录位置,从该目录读取pdf课件
srcrootpath = './../../data/course-knowledge-machine/' + dirname
c_rootpath = srcrootpath + '/c-docx'
#q_rootpath = srcrootpath + '/q-xlsx'
self.loadProcessedCourse(srcrootpath)
# os.walk(path)这个函数得到的结果是一个或多个tuple，
# 或者使用os.listdir(path)函数能得到文件夹下所有文件（包括文件夹）的名称，但是无法获取子文件夹的状态
count = 0
filelist = self.get_filename_from_dir(c_rootpath)
# 然后是对每一个文件进行处理
for f in filelist:
count = count + 1
self.coursename = os.path.splitext(f)[0]
# 判断该课程是否在需要处理的范围之内，如果不是，则跳过该课程
current_coursename = self.getCourseNameFromFileName(
self.coursename)
current_schoolname = self.getSchoolNameFromFileName(
self.coursename)
if not self.school_course_scope_dict.__contains__(
current_schoolname + current_coursename):
self.course_over_scope.append(f)
continue
# 如果课程名称中包含英语，不处理
if current_coursename.__contains__(u'英语'):
continue
# 如果该课程在需要处理的范围内，则开始处理
print '开始处理文件：{}'.format(f)
course = self.school_course_scope_dict.get(current_schoolname +
current_coursename)
if len(course.SchoolName) == 0:
self.course_unrecongnized.append(f)
continue
# 如果课程已经被处理了，跳过
course_key = '{}-{}'.format(course.SchoolCode, course.CourseCode)
if self.course_processed_dict.__contains__(course_key):
print '第{0}篇 课程：{1} 已处理过；'.format(count, f)
continue
course_path_info = CourseInfomation.CourseFilepath()
# 指定课件的源文件路径
course_path_info.courseware_source_directory = srcrootpath
course_path_info.courseware_source_docx_filepath = c_rootpath + '/' + f
#course_path_info.examquestion_source_xlsx_filepath = q_rootpath + '/' + current_coursename + '.xlsx'
course_path_info.initByCourse(course)
# 如果已经关联过了，不用再次关联
self.associateFlow(course_path_info)
print '第{0}篇 课程：{1} 处理完成；'.format(count, f)
# 测试时，先跑4个文件即可
if self.isTest:
if count > 4:
break
print '所有课程处理完毕，共处理：{0}篇'.format(count)
# 开始统计结果
print '开始统计结果。'
statistics_filepath = '{}/statistics.txt'.format(srcrootpath)
self.statistics(statistics_filepath)
print '统计结果结束。'
# 关联差的数据保存
combine_bad_filepath = '{}/combine_bad.xls'.format(srcrootpath)
self.combineBadExamquestion(combine_bad_filepath)
continue
if word.startswith(u'概'):
continue
result_list.append(word)
return result_list
def outfile(self, filepath):
fout = open(filepath, 'w')
fout.writelines(self.snd_level_catalog)
fout.close()
if __name__ == "__main__":
course_path_info = CourseInfomation.CourseFilepath()
course_path_info.courseware_source_txt_filepath = u'./../../data/course-base/本科专业目录-catalog.xlsx.txt'
course_path_info.vector_corpus_txt_filepath = u'./../../data/course-base/本科专业目录-catalog.corpus.txt'
course_path_info.vector_model_bin_filepath = u'./../../data/course-base/本科专业目录-catalog.model.bin'
course_path_info.correlation_txt_filepath = u'./../../data/course-base/本科专业目录-course-catalog.txt'
sr = TextVector(course_path_info)
#sr.course_path_info = course_path_info
sr.readCourseNameList()
sr.train()
sr.predication()
sr.output_dict()
filepath = u'./../../data/course-base/本科专业目录-course-catalog-tag.txt'
sr.outfile(filepath)
def predication(self):
self.bad_examquestion_list = []
self.course_score = CourseInfomation.CourseScore()
self.course_score.initCourse(self.course_path_info_list[0].course)
# match(n)-[:NEXT]-(m) where n.name in ['典型','金本位制','指','金币','本位'] return n,m
if self.examquestion_info is None:
return
qindex = 0
question_knowledge_map = {}
for course_path_info in self.course_path_info_list:
if not self.examquestion_info.examquestion_dict.__contains__(
course_path_info.course):
return
exam_question_list = self.examquestion_info.examquestion_dict.get(
course_path_info.course)
for exam_question in exam_question_list:
#line = "物权的分类:从设立的角度对他物权再做分类，可把其分为（）。,用益物权和担保物权"
k = exam_question.knowledge_list
q = exam_question.getContentAndAnswer()
question_knowledge_map[q] = k
qindex = qindex + 1
q_words = self.sentence.splitSentenceCanRepeat(q)
# 从q中找重点词, 并放大重点词
q_words = self.preprocessor.enlargeVipWords(q_words, q)
if len(q_words) == 0:
continue
# 然后再遍历知识点
index = 0
res_list = []
for k_key in self.knowledge.keys():
k_tup = self.knowledge.get(k_key)
k_words = k_tup[0]
if len(k_words) == 0:
continue
score = self.doc_vec.pred_similarity(q_words, k_words)
res = ResultInfo.ResultInfo(index, score, k_tup[2], k_key)
res_list.append(res)
index += 1
# 对列表按score降序排列
res_list.sort(cmp=None, key=lambda x: x.score, reverse=True)
# 取分值最高的几个，超过1%，的舍去，或者再限定具体数量，比如3个
# 统计得分的情况
self.computeScore(res_list)
# 统计不超过50分的试题
if self.badExamquestionStatistics(res_list) == True:
self.bad_examquestion_list.append(
(exam_question, res_list[0:3]))
# 获取上级 知识点
#reslist = self.getParentKnowledge(reslist)
# 格式化输出
reslist, wordlist = self.formatOutput(res_list, k)
# 统计正确率
if len(reslist) > 0:
ns = '问题{0}:'.format(qindex) + q
self.outputcontentlist.append(ns + '\n')
ns = '电脑标识知识点:' + ';'.join(wordlist)
self.outputcontentlist.append(ns + '\n')
ns = '知识点评估指标:' + ';'.join(reslist)
self.outputcontentlist.append(ns + '\n')
#print '老师标识知识点:' + k
ns = '老师标识知识点:'
self.outputcontentlist.append(ns + '\n')
self.outputcontentlist.append('\n')
#ns = '电脑标识是否正确:'
#self.outputcontentlist.append(ns)
# 计算正确率
# 题目总数
self.course_score.compute()
ns = '试题总数：{}'.format(self.course_score.score_scope_total)
self.outputcontentlist.append(ns + '\n')
print ns
ns = '比较靠谱数(60分以上)：{} ，比较靠谱占比：{}%'.format(
self.course_score.score_scope_more60_count,
round(self.course_score.score_scope_more60_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '基本靠谱数(50-60分)：{} ，基本靠谱占比：{}%'.format(
self.course_score.score_scope_between5060_count,
round(self.course_score.score_scope_between5060_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不太靠谱数(40-50分)：{} ，不太靠谱占比：{}%'.format(
self.course_score.score_scope_between4050_count,
round(self.course_score.score_scope_between4050_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不靠谱数(40分以下)：{} ，不靠谱占比：{}%'.format(
self.course_score.score_scope_less40_count,
round(self.course_score.score_scope_less40_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
def predication(self):
# match(n)-[:NEXT]-(m) where n.name in ['典型','金本位制','指','金币','本位'] return n,m
if self.input_subject_file is None:
self.input_subject_file = self.doc_vec.train_input_subject_file
question = open(self.input_subject_file, 'r')
ids_lines = question.readlines()
qindex = 0
question_knowledge_map = {}
self.course_score = CourseInfomation.CourseScore()
for line in ids_lines:
#line = "物权的分类:从设立的角度对他物权再做分类，可把其分为（）。,用益物权和担保物权"
line = line.strip('\n')
index = line.index(':')
k = line[0:index]
q = line[index + 1:]
question_knowledge_map[q] = k
qindex = qindex + 1
q_words = self.sentence.splitSentenceCanRepeat(q)
# 从q中找重点词, 并放大重点词
q_words = self.preprocessor.enlargeVipWords(q_words, q)
if len(q_words) == 0:
continue
# 然后再遍历知识点
index = 0
res_list = []
for k_key in self.knowledge.keys():
k_tup = self.knowledge.get(k_key)
k_words = k_tup[0]
if len(k_words) == 0:
continue
score = self.doc_vec.pred_similarity(q_words, k_words)
res = ResultInfo.ResultInfo(index, score,
k_tup[2] + ' ' + k_key)
res_list.append(res)
index += 1
# 对列表按score降序排列
res_list.sort(cmp=None, key=lambda x: x.score, reverse=True)
# 取分值最高的几个，超过1%，的舍去，或者再限定具体数量，比如3个
# 统计得分的情况
self.computeScore(res_list)
# 获取上级 知识点
#reslist = self.getParentKnowledge(reslist)
# 格式化输出
reslist, wordlist = self.formatOutput(res_list)
# 统计正确率
if len(reslist) > 0:
ns = '问题{0}:'.format(qindex) + q
self.outputcontentlist.append(ns + '\n')
ns = '电脑标识知识点:' + ';'.join(wordlist)
self.outputcontentlist.append(ns + '\n')
ns = '知识点评估指标:' + ';'.join(reslist)
self.outputcontentlist.append(ns + '\n')
#print '老师标识知识点:' + k
ns = '老师标识知识点:' + k
self.outputcontentlist.append(ns + '\n')
self.outputcontentlist.append('\n')
#ns = '电脑标识是否正确:'
#self.outputcontentlist.append(ns)
# 计算正确率
# 题目总数
self.course_score.compute()
ns = '试题总数：{}'.format(self.course_score.score_scope_total)
self.outputcontentlist.append(ns + '\n')
print ns
ns = '比较靠谱数(60分以上)：{} ，比较靠谱占比：{}%'.format(
self.course_score.score_scope_more60_count,
round(self.course_score.score_scope_more60_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '基本靠谱数(50-60分)：{} ，基本靠谱占比：{}%'.format(
self.course_score.score_scope_between5060_count,
round(self.course_score.score_scope_between5060_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不太靠谱数(40-50分)：{} ，不太靠谱占比：{}%'.format(
self.course_score.score_scope_between4050_count,
round(self.course_score.score_scope_between4050_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不靠谱数(40分以下)：{} ，不靠谱占比：{}%'.format(
self.course_score.score_scope_less40_count,
round(self.course_score.score_scope_less40_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
k_list = []
f = open(self.ngram.outputfile)
for k in f:
k_list.append(k)
return k_list
if __name__ == "__main__":
pusher = TreeFactory()
sen = u'“诗史”'
sen = pusher.postProcessSentence(sen)
sen = u'协议出让33.4%表 2．招标出让22%图3．折扣（discount为'
pattern = re.compile(pusher.re_nouse_tag_percent)
res = pattern.findall(sen)
pusher.outputfile = u'./../data/course-knowledge-tgt/抽取模板.txt'
pusher.inputfile = u'D:/奥鹏/学生服务中心标注/文科课程电子辅导资料-docx/抽取模板.docx'
course_filepath = CourseInfomation.CourseFilepath()
course_filepath.sourse_filetype = course_filepath.type_text
course_filepath.courseware_source_txt_filepath = u'./../../data/other/中级财务会计.txt'
course_filepath.courseware_knowledge_txt_filepath = u'./../../data/other/中级财务会计-kwg.txt'
course = CourseInfomation.Course()
course.CourseCode = '1000'
course_filepath.course = course
pusher.course_filepath = course_filepath
pusher.extractKnowledge()
print 'over.'