jours = dict([(journal['中文名称'],journal.get('复合影响因子')) for journal in journals])
jours_set = jours.keys()
STEP_ONE = False
STEP_TWO = True
# 2. 进行CNKI网站操作
if STEP_ONE:
cnki_obj = Cnki()
#cnki_obj = Cnki(PROXY_LIST[random.randint(0,len(PROXY_LIST)-1)])
cnki_obj.set_query(QUERY_STRING)
cnki_obj.set_period(start_period=START_PERIOD,end_period=END_PERIOD)
cnki_obj.set_subject(subjects=SUBJECTS)
cnki_obj.submit()
cnki_obj.sort()
cnki_obj.select_all_literature()
cnki_obj.child_operation()
cnki_obj.get_more()
cnki_obj.export_to_json(file=LITERATURE_JSON_FILE)
cnki_obj.close()
if STEP_TWO:
literatures = json.load(open(LITERATURE_JSON_FILE))
for liter in literatures:
paper_dict = literatures[liter]
paper_dict['title'] = liter
print(paper_dict)
if paper_dict['journal'] in jours_set:
paper_dict['rate'] = ''.join([str(jours[paper_dict['journal']]),'-',paper_dict['ISBN/ISSN']])
else:
class CnkiLiterature:
""" CnkiLiterature类用来自动化cnki文献搜索
"""
def __init__(self,proxy=None):
self.__jounal_db = ChinaJournalDatabase()
self.__literatrues = None
if proxy is None:
self.cnki_obj = Cnki()
else:
self.cnki_obj = Cnki(proxy=proxy)
def query(self,query_str=None,start_period=None,end_period=None,sort_by='被引',
limit=4,subjects=['经济与管理科学']):
""" 查询
:param str query_str: 查询字符串
:param str start_period: 起始年份
:param str end_period: 终止年份
:param str sort_by: 排序
:param int limit: 搜索限制数
:param list subjects: 学科
:return: 无返回值
"""
# 设定查询字符串
self.cnki_obj.set_query(query_str)
# 设定起始日期
self.cnki_obj.set_period(start_period=start_period,end_period=end_period)
# 设定领域
self.cnki_obj.set_subject(subjects=subjects)
# 确定搜索
self.cnki_obj.submit()
# 排序
self.cnki_obj.sort(by=sort_by)
# 选择所有的文献
self.cnki_obj.select_all_literature()
# 后续操作
self.cnki_obj.child_operation()
# 更多的文献
self.cnki_obj.get_more(limit=limit)
self.__literatrues = self.cnki_obj.export_to_dict()
def sort_by(self,by=None):
""" 对查询结果排序
:param str by: 排序根据
:return: 无返回值
"""
for item in self.__literatrues:
paper = self.__literatrues[item]
paper['title'] = item
journal = self.__jounal_db.getByName(journal_name=paper['journal'],auto=True)
if len(journal) < 1:
paper['rate'] = '---'.join(['0',paper['title']])
else:
paper['rate'] = '---'.join([str(journal[0][by]),paper['title']])
tmp_result = dict([(self.__literatrues[item]['rate'],self.__literatrues[item])
for item in self.__literatrues])
for key in tmp_result:
del tmp_result[key]['rate']
self.__literatrues = [tmp_result[item] for item in sorted(tmp_result,reverse=True)]
def export_to_pdf(self,out_file,title='',abstract=''):
""" 输出文献综述到pdf文件
:param out_file: 文档名称
:param title: 文档标题
:param abstract: 文档摘要
:return: 无返回值
"""
replace_word = {'articleTitle':title,'arcticleabstract':abstract}
doc = Article(r'E:\gitrobot\files\latex_template\article_template_01.tex',replace_word)
for item in self.__literatrues:
doc.document.add_section(item['title'],3)
doc.document.add_list(['---'.join([item['journal'],item['year']])],type=1)
doc.document.append(item['abstract'].encode().decode())
doc.document.generate_tex(out_file)
doc.document.generate_pdf(out_file)
@property
def literatrues(self):
""" 文献
:return: 文献
"""
return self.__literatrues
def close(self):
""" 关闭浏览器
:return: 无返回值
"""
self.cnki_obj.close()