def getBrief(this):
'''
抽取scholar的个人简介
'''
pathBasic = '//*[contains(@class,"ant-tabs-nav-list")]/*[1]'
path = '//*[contains(@class,"active")]//*[contains(@class,"bio")]'
basic = this.__dv.find_elements_by_xpath(pathBasic)
if not basic: return None
basic = basic[0]
this.__clickIfNotActive(basic, waitLoading, path)
return getTextByXpath(this.__dv, path)
def getExperience(this):
'''
抽取scholar的工作经历
'''
pathBasic = '//*[contains(@class,"ant-tabs-nav-list")]/*[1]'
path = '//*[contains(@class,"active")]//*[@class="aff_inst"]/div'
basic = this.__dv.find_elements_by_xpath(pathBasic)
if not basic: return None
basic = basic[0]
this.__clickIfNotActive(basic, waitLoading, path)
return getTextByXpath(this.__dv, path)
def getPapers(this):
'''
抽取scholar的论文（按引用量降序的一页，以便去重）
'''
###“学术成果”标签，可点击
pathAchievements = '//*[contains(@class,"ant-tabs-nav-list")]/*[2]'
###发表论文or科研项目
pathPP = '//*[contains(@class,"ant-tabs-nav-list")]/*[2]/self::*[contains(@class,"active")]/../../../..//span[@class="title"]'
###“按引用量排序”标签，可点击
pathRefSort = '//*[contains(@class,"pubs_sort_line")]/div/*[2]'
###论文标签
pathPaper = '//*[contains(@class,"pubs_sort_line")]/div'\
'/*[2]/self::*[contains(@class,"active")]/../../../../..'\
'//*[@class="content"]'
###论文id相对路径
pathId = '..'
###论文题目相对路径
pathTitle = './/*[contains(@class,"title")]/span'
###论文作者相对路径
pathAuthor = './/*[contains(@class,"authors")]'
###论文期刊相对路径
pathVenue = './/*[contains(@class,"venue-line")]'
###论文引用量相对路径
pathCited = './/*[@class="cited"]/strong'
###加载等待中
pathLoading = '//*[contains(@class,"sk_chase")]'
###没有论文
pathNodata = '//div[contains(@class,"profilePapers___1bMnJ")]//img[contains(@src,"noData")]'
###是否有论文
pathHavePapers = '//div[contains(@class,"profilePapers___1bMnJ")]//*[@class="content"]'
###点击“学术成果”
achievements = this.__dv.find_elements_by_xpath(pathAchievements)
if not achievements: return []
achievements = achievements[0]
###没有“学术成果”键
if 'disabled' in achievements.get_attribute('class'):
return []
this.__clickIfNotActive(achievements, waitLoading, pathPP)
###点击“按引用量排序”
if not this.__dv.find_elements_by_xpath(pathHavePapers): return []
refSort = this.__dv.find_elements_by_xpath(pathRefSort)
if not refSort: raise Exception("no sort by reference")
refSort = refSort[0]
this.__clickIfNotActive(refSort, waitLoading,
pathPaper + '|' + pathNodata, 1)
if not waitTillLoaded(
this.__dv, waitLoading, value=pathLoading, waitUnit=waitUnit):
raise Exception("load failed")
if this.__dv.find_elements_by_xpath(pathNodata): return []
###抽取结果
papers = this.__dv.find_elements_by_xpath(pathPaper)
return [{
"id": stdAminerId(getAttributeByXpath(p, pathId, 'id')),
"title": getTextByXpath(p, pathTitle),
"authors": rmUnseen(getTextByXpath(p, pathAuthor)),
"venue": getTextByXpath(p, pathVenue),
"cited": getTextByXpath(p, pathCited)
} for p in papers]
def getAddress(this):
'''
抽取scholar的住址
'''
path = '//*[contains(@class,"map-marker")]/../span'
return getTextByXpath(this.__dv, path)
def getFax(this):
'''
抽取scholar的传真
'''
path = '//*[contains(@class,"fax")]/../span'
return getTextByXpath(this.__dv, path)
def getEmail(this):
'''
抽取scholar的email
'''
path = '//*[contains(@class,"envelope")]/../span'
return getTextByXpath(this.__dv, path)
def getPhone(this):
'''
抽取scholar的电话
'''
path = '//*[contains(@class,"phone")]/../span'
return getTextByXpath(this.__dv, path)
def getDepartment(this):
'''
抽取scholar的机构
'''
path = '//*[contains(@class,"institution")]/../span'
return getTextByXpath(this.__dv, path)
def getTitle(this):
'''
抽取scholar的职称
'''
path = '//*[contains(@class,"briefcase")]/../span'
return getTextByXpath(this.__dv, path)