class EconPapers:
""" EconPapers类获取和解析EconPapers网站内容
:param str journal_web: 杂志首页
:return: 无返回值
"""
def __init__(self,journal=None,journal_web=None):
self.journal_web = journal_web
self.scraper = SiteScraper(journal_web)
# 期刊名称
self.journal = journal
# 网页集合
self.literature_websites = None
# 文献信息列表
self.literature_info = list()
def to_literature_websites(self,condition=None,filter=None):
""" 构建文献网址的列表
:param str condition: 筛选条件
:param str filter: 过滤条件
:return: 无返回值
"""
self.scraper.get_links(page_url="",condition=condition)
pages = self.scraper.pages
if filter is not None:
pages = (page for page in pages if re.search(filter,page) is not None)
self.literature_websites = [''.join([self.journal_web,page]) for page in pages]
def get_literature_info(self,websites=None):
""" 利用网页信息获取文献信息
:param str,list websites: 网页地址
:return: 无返回值
"""
if websites is None:
websites = self.literature_websites
if isinstance(websites,str):
websites = [websites]
i = 0
for web in websites:
print(i)
econ_parser = EconPapersLitPageParser(page=web,journal=self.journal)
self.literature_info.append(econ_parser.literature_info)
i += 1
def export_literature_websites(self,file):
""" 导出文献网址
:param str file: 导出的文件名
:return: 无返回值
"""
json.dump(self.literature_websites, fp=open(file,'w'))
def __init__(self,journal=None,journal_web=None):
self.journal_web = journal_web
self.scraper = SiteScraper(journal_web)
# 期刊名称
self.journal = journal
# 网页集合
self.literature_websites = None
# 文献信息列表
self.literature_info = list()
