Python Formatter.data方法代码示例

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
def getHealthNews(lan='en',format='json'):
	returnData = MutableString()
	returnData = ''
	if (lan == 'es'):
		dom = minidom.parse(urllib.urlopen(AppConfig.medlinePlusHealthNewsSpanishURL))
	else:
		dom = minidom.parse(urllib.urlopen(AppConfig.medlinePlusHealthNewsEnglishURL))
	rssTitle = MutableString()
	rssDescription = MutableString()
	rssURL = MutableString()
	for node in dom.getElementsByTagName('item'):
		for item_node in node.childNodes:
			rssTitle = ''
			rssDescription = ''
			rssURL = ''
			#item title
			if (item_node.nodeName == "title"):
				for text_node in item_node.childNodes:
					if (text_node.nodeType == node.TEXT_NODE):
						rssTitle += text_node.nodeValue
			#description
			if (item_node.nodeName == "description"):
				for text_node in item_node.childNodes:
					rssDescription += text_node.nodeValue
			#link to URL
			if (item_node.nodeName == "link"):
				for text_node in item_node.childNodes:
					rssURL += text_node.nodeValue
			
			if (format == 'json'):
				startTag = '{'
				endTag = '},'
				
				#cleanup
				#rssTitle = re.sub("\"", "'", rssTitle)
				rssTitle = re.sub("\n", "", rssTitle)
				rssTitle = re.sub("\"", "\\\"", rssTitle)
				rssDescription = re.sub("\"", "\\\"", rssDescription)
				rssDescription = re.sub("\n", "", rssDescription)
				rssDescription = re.sub("\t", " ", rssDescription)
				rssDescription = re.sub("\r", "", rssDescription)
				
				if (len(rssDescription) > 0):
					rssDescription = Formatter.data(format, 'description', escape(rssDescription))[:-1]
			else:
				startTag = '<record>'
				endTag = '</record>'		
				if (len(rssDescription) > 0):
					rssDescription = Formatter.data(format, 'description', escape(rssDescription))								
			
			if (len(rssTitle) > 0):
				returnData += startTag + Formatter.data(format, 'title', rssTitle)
				
			if (len(rssURL) > 0):
				returnData += Formatter.data(format, 'url', rssURL) 
			
			if (len(rssDescription) > 0 ):
				returnData += rssDescription + endTag
	
	return returnData

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
	def getDiagnosisICD9Data(self,xml,format):
		if (xml):
			documentElms = xml.getElementsByTagName('entry')
			if (documentElms):
				#grab two highest ranked content
				content1 = ''
				content2 = ''
				
				contentNode1 = documentElms[0]
				content1 = APIUtils.parseHealthDiagnosisICD9Content(format,contentNode1)
				
				if (len(documentElms) > 0):
					contentNode2 = documentElms[1]
					content2 = APIUtils.parseHealthDiagnosisICD9Content(format,contentNode2)
				
				returnData = "%s%s" % (content1, content2)
				if (format == 'json'):
					return returnData[:-1]
				else:
					return returnData		
			else:
				logging.error('unable to retrieve diagnosis content')
				return Formatter.data(format, 'error', 'No results')
		else:
			logging.error('unable to retrieve diagnosis content')
			return Formatter.data(format, 'error', 'Unable to retrieve content from provider')

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
	def get(self,zip=None,format='json'):
		#set content-type
		self.response.headers['Content-Type'] = Formatter.contentType(format)
		
		#validate zip
		if (not zip or zip == ''):
			self.response.out.write(Formatter.error(format, 'invalid zipcode'))
			return
	
		#get lat/lon from zipcode
		urlStr = 'http://maps.google.com/maps/geo?q=%s&output=json&sensor=true&key=%s' % (zip,AppConfig.googleMapsAPIKey)
		jsonData = UtilLib.reverseGeo(urlStr)	
		#lets see if have jsonData from reverse geocoding call
		if (jsonData):
			lon = jsonData['Placemark'][0]['Point']['coordinates'][0]
			lat = jsonData['Placemark'][0]['Point']['coordinates'][1]
			logging.debug("GPS Coordinates: %s,%s" % (lat,lon))
			gb = geobox2.Geobox(lat, lon)
			#scope 100 miles
			box = gb.search_geobox(100)
			query = HospitalInfo.all().filter("geoboxes IN", [box])
			#get 100 records
			results = query.fetch(100)
			db_recs = {}
			for result in results:
				distance = UtilLib.getEarthDistance(lat, lon, result.location.lat, result.location.lon)
				if (distance and distance > 0):
					db_recs[distance] = result
			
			returnData = MutableString()
			returnData = ''
					
			#output this badboy
			if (db_recs and len(db_recs) > 0):
				for key in sorted(db_recs.iterkeys()):
					p = db_recs[key]
					if (format == 'json'):
						startTag = '{'
						endTag = '},'
						distance = Formatter.data(format, 'distance', '%s %s' % (str(math.ceil(key)), "mi"))[:-1]#'%.2g %s' % (key, "mi"))[:-1]
					else:
						startTag = '<record>'
						endTag = '</record>'
						distance = Formatter.data(format, 'distance', '%s %s' % (str(math.ceil(key)), "mi"))
					#build the string	
					returnData = "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s" % (returnData,startTag,
																Formatter.data(format, 'hospital_id', p.hospital_id),
																Formatter.data(format, 'name', p.name.replace('&', '&amp;')),
																Formatter.data(format, 'address', p.address.replace('&', '&amp;')),
																Formatter.data(format, 'city', p.city),
																Formatter.data(format, 'state', p.state),
																Formatter.data(format, 'zip_code', p.zip_code),
																Formatter.data(format, 'county', p.county.replace('&', '&amp;')),
																Formatter.data(format, 'phone', p.phone),
																Formatter.data(format, 'hospital_type', p.hospital_type.replace('&', '&amp;')),
																Formatter.data(format, 'hospital_owner', p.hospital_owner.replace('&', '&amp;')),
																Formatter.data(format, 'emergency_service', p.emergency_service),
																Formatter.data(format, 'geo_location', p.location),
																distance,
																endTag
																)
																 
			
			#output to the browser
			self.response.out.write(Formatter.dataWrapper(format, returnData))
		else:
			self.response.out.write(Formatter.error(format, 'Unable to perform reverse geoencoding'))
			return

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
	def getHospitalData(self,lat,lon,format):
		#get hospital data
		gb = geobox2.Geobox(lat, lon)
		box = gb.search_geobox(100)
		query = HospitalInfo.all().filter("geoboxes IN", [box])
		results = query.fetch(100)
		db_recs = {}
		for result in results:
			distance = UtilLib.getEarthDistance(lat, lon, result.location.lat, result.location.lon)
			if (distance and distance > 0):
				db_recs[distance] = result
		
		returnData = MutableString()
		returnData = ''

		#output this badboy
		if (db_recs and len(db_recs) > 0):
			for key in sorted(db_recs.iterkeys()):
				p = db_recs[key]
				if (format == 'json'):
					startTag = '{'
					endTag = '},'
					distance = Formatter.data(format, 'distance', '%s %s' % (str(math.ceil(key)), "mi"))[:-1]#'%.2g %s' % (key, "mi"))[:-1]
				else:
					startTag = '<record>'
					endTag = '</record>'
					distance = Formatter.data(format, 'distance', '%s %s' % (str(math.ceil(key)), "mi"))
				#build the string	
				returnData = "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s" % (returnData,startTag,
															Formatter.data(format, 'hospital_id', p.hospital_id),
															Formatter.data(format, 'name', p.name.replace('&', '&amp;')),
															Formatter.data(format, 'address', p.address.replace('&', '&amp;')),
															Formatter.data(format, 'city', p.city),
															Formatter.data(format, 'state', p.state),
															Formatter.data(format, 'zip_code', p.zip_code),
															Formatter.data(format, 'county', p.county.replace('&', '&amp;')),
															Formatter.data(format, 'phone', p.phone),
															Formatter.data(format, 'hospital_type', p.hospital_type.replace('&', '&amp;')),
															Formatter.data(format, 'hospital_owner', p.hospital_owner.replace('&', '&amp;')),
															Formatter.data(format, 'emergency_service', p.emergency_service),
															Formatter.data(format, 'geo_location', p.location),
															distance,
															endTag
															)
	
			if (format == 'json'):
				return returnData[:-1]
			else:
				return returnData

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
	def getTopicData(self,xml,format,lan='en'):
		if (xml):
			documentElms = xml.getElementsByTagName('document')
			if (documentElms):
				#grab two highest ranked content
				content1 = ''
				content2 = ''
				content3 = ''
				
				contentNode1 = documentElms[0]
				content1 = APIUtils.parseHealthTopicContent(format,contentNode1)
				
				if (len(documentElms) > 1):
					contentNode2 = documentElms[1]
					content2 = APIUtils.parseHealthTopicContent(format,contentNode2)
				
				if (len(documentElms) > 2):
					contentNode3 = documentElms[2]
					content3 = APIUtils.parseHealthTopicContent(format,contentNode3)
				
				returnData = "%s%s%s" % (content1, content2, content3)
				
				"""
				Giving up for now....major pain in the butt to translate entire XML or JSON document
				
				#fun stuff: lets see if we need to translate
				#because we have three content records it's better to 
				#translate the entire document (json or xml) instead of individual content summaries
				translatedData = ''
				if (lan != 'en'):
					#prep data
					#if JSON, replace record definition with non-translatable text
					if (format == 'json'):
						returnData = re.sub("\"", "X59X", returnData)
					else:
						#get rid of the tags. Google Translate doesn't seem to like them
						returnData = returnData#CharReplacementMap.translate_tags_from_xml_record(returnData)
					
					translatedData = self.translateData(lan,returnData.encode("utf-8"))
					self.out(translatedData)
					
									
				if (translatedData):
					#cheesy search&replace - need a quick solution to fix JSON
					if (format == 'json'):
						translatedData = re.sub("X59X","\"", translatedData)
						translatedData = re.sub("\n", "", translatedData)
						translatedData = re.sub("\r", "", translatedData)
						translatedData = re.sub("\t", "", translatedData)
					else:
						translatedData = translatedData#CharReplacementMap.translate_tags_to_xml_record(translatedData)
					
					return translatedData
				"""	
				if (format == 'json'):
					return returnData[:-1]
				else:
					return returnData
			else:
				logging.error('unable to retrieve health topic content')
				return Formatter.data(format, 'error', 'No results')
		else:
			logging.error('unable to retrieve health topic content')
			return Formatter.data(format, 'error', 'Unable to retrieve content from provider')

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
		#get hospital data
		if (userLat and userLon):
			hospitalData = self.getHospitalData(userLat, userLon,format)
			if (hospitalData):
				returnData += Formatter.dataComplex(format, 'hospital-records', hospitalData)
		
		if (rpcClinicalTrials):
			clinicalTrialsData = ''
			try:
			    resultClinicalTrials = rpcClinicalTrials.get_result()
			    if (resultClinicalTrials and resultClinicalTrials.status_code == 200):
					if (resultClinicalTrials.content):
						clinicalTrialsData = self.getClinicalTrialsData(minidom.parseString(resultClinicalTrials.content), format)
					else:
						logging.error('unable to retrieve clinical trials content')
						clinicalTrialsData = Formatter.data(format, 'error', 'Unable to retrieve content from provider')
			except Exception,ex:
				logging.error('Errors getting clinical trials content: %s' % ex)
				clinicalTrialsData = Formatter.data(format, 'error', 'Error(s) retrieving content from provider: %s' % ex)
		
			#append to the overall dataset
			returnData += Formatter.dataComplex(format, 'clinicaltrials-records', clinicalTrialsData)
		
		#fetch ICD-9 diagnosis data
		if (rpcDiagnosis):
			diagnosisData = ''
			try:
			    resultDiagnosis = rpcDiagnosis.get_result()
			    if (resultDiagnosis and resultDiagnosis.status_code == 200):
					if (resultDiagnosis.content):
						diagnosisData = self.getDiagnosisICD9Data(minidom.parseString(resultDiagnosis.content), format)

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
def parseHealthTopicContent(format,node):
	if (node):
		contentTitle = MutableString()
		contentAltTitle = MutableString()
		contentSummary = MutableString()
		contentTitle = ''
		contentAltTitle = ''
		contentSummary = ''
		
		for content_node in node.childNodes:
			#get title
			if (content_node and content_node.nodeName == 'content' and content_node.attributes['name'].value == "title"):
				for text_node in content_node.childNodes:
					contentTitle += CharReplacementMap.remove_html_tags(text_node.nodeValue)
			#get alt title
			"""if (content_node and content_node.nodeName == 'content' and content_node.attributes['name'].value == "altTitle"):
				for text_node in content_node.childNodes:
					contentAltTitle += remove_html_tags(text_node.nodeValue)
			"""
			#get content	
			if (content_node and content_node.nodeName == 'content' and content_node.attributes['name'].value == "FullSummary"):
				for text_node in content_node.childNodes:
					contentSummary += text_node.nodeValue
		
		#replace HTML tags with friendly tags (that will be replaced back to HTML later)
		#contentSummary = CharReplacementMap.translate_tags_from_html(contentSummary)
		#now strip HTML garbage
		#contentSummary = CharReplacementMap.remove_html_tags(contentSummary)
		
		returnData = MutableString()
		returnData = ''			
		if (format == 'json'):
			startTag = '{'
			endTag = '},'
			
			#cleanup
			contentTitle = re.sub("\n", "", contentTitle)
			contentTitle = re.sub("\"", "\\\"", contentTitle)
			contentAltTitle = re.sub("\n", "", contentAltTitle)
			contentAltTitle = re.sub("\r", "", contentAltTitle)
			contentAltTitle = re.sub("\"", "\\\"", contentAltTitle)
			contentSummary = re.sub("\"", "\\\"", contentSummary)
			contentSummary = re.sub("\n", "", contentSummary)
			contentSummary = re.sub("\t", " ", contentSummary)
			contentSummary = re.sub("\r", "", contentSummary)
			
			if (len(contentSummary) > 0):
				contentSummary = Formatter.data(format, 'summary', escape(contentSummary))[:-1]
		else:
			startTag = '<record>'
			endTag = '</record>'		
			if (len(contentSummary) > 0):
				contentSummary = Formatter.data(format, 'summary', escape(contentSummary))
		
		if (len(contentTitle) > 0):
			returnData += startTag + Formatter.data(format, 'title', escape(contentTitle))

		if (len(contentAltTitle) > 0):
			returnData += Formatter.data(format, 'alt_title', escape(contentAltTitle)) 

		if (len(contentSummary) > 0 ):
			returnData += contentSummary + endTag

		return returnData

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
def parseClinicalTrialsContent(format,node):
	if (node):
		contentTitle = MutableString()
		contentLink = MutableString()
		contentSummary = MutableString()
		contentStatus = MutableString()
		contentTitle = ''
		contentLink = ''
		contentSummary = ''
		contentStatus = ''

		for content_node in node.childNodes:
			#get title
			if (content_node and content_node.nodeName == 'title'):
				for text_node in content_node.childNodes:
					contentTitle += text_node.nodeValue
			#get link
			if (content_node and content_node.nodeName == 'url'):
				for text_node in content_node.childNodes:
					contentLink += text_node.nodeValue
			#get status
			if (content_node and content_node.nodeName == 'status'):
				for text_node in content_node.childNodes:
					contentStatus += text_node.nodeValue
			#get content	
			if (content_node and content_node.nodeName == 'condition_summary'):
				for text_node in content_node.childNodes:
					contentSummary += text_node.nodeValue

		returnData = MutableString()
		returnData = ''			
		if (format == 'json'):
			startTag = '{'
			endTag = '},'

			#cleanup
			contentStatus = re.sub("\n", "", contentStatus)
			contentStatus = re.sub("\"", "\\\"", contentStatus)
			contentTitle = re.sub("\n", "", contentTitle)
			contentTitle = re.sub("\"", "\\\"", contentTitle)
			contentTitle = re.sub("\t", " ", contentTitle)
			contentLink = re.sub("\n", "", contentLink)
			contentLink = re.sub("\"", "\\\"", contentLink)
			contentSummary = re.sub("\"", "\\\"", contentSummary)
			contentSummary = re.sub("\n", "", contentSummary)
			contentSummary = re.sub("\t", " ", contentSummary)

			if (len(contentSummary) > 0):
				contentSummary = Formatter.data(format, 'summary', escape(contentSummary))[:-1]
		else:
			startTag = '<record>'
			endTag = '</record>'		
			if (len(contentSummary) > 0):
				contentSummary = Formatter.data(format, 'summary', escape(contentSummary))

		if (len(contentTitle) > 0):
			returnData += startTag + Formatter.data(format, 'title', escape(contentTitle))

		if (len(contentLink) > 0):
			returnData += Formatter.data(format, 'link', escape(contentLink)) 

		if (len(contentStatus) > 0):
			returnData += Formatter.data(format, 'status', escape(contentStatus))

		if (len(contentSummary) > 0 ):
			returnData += contentSummary + endTag

		return returnData

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]

#.........这里部分代码省略.........
			if (key in comments_stuff):
				tupComments = comments_stuff[key]
			else:
				tupComments = None
			if (tupURL):
				url = ''
				title = ''
				score = ''
				user = ''
				comments = ''
				timeAgo = ''
				itemId = ''
				itemInfo = ''
				
				#assign vars
				url = tupURL[0]
				title = tupURL[1]
				
				if (tupComments):
					score = tupComments[0]
					user = tupComments[1]
					comments = tupComments[2]
					timeAgo = tupComments[3]
					itemId = tupComments[4]
					itemInfo = tupComments[5]
				else:
					#need this for formatting
					itemInfo = 'n/a '
				
				#last record (either news2 or x?fnid)
				if (title.lower() == 'more' or '/x?fnid' in url):
					title = 'NextId'
					if ('/x?fnid' in url):
						url = '%s/format/%s/page/%s' % (apiURL, format, url.replace('/x?fnid=', ''))
					else:
						url = '/news2'
					itemInfo = 'hn next id %s ' % tupURL[0]
				
				if (format == 'json'):
					startTag = '{'
					endTag = '},'
					
					#cleanup
					if (title):
						title = re.sub("\n", "", title)
						title = re.sub("\"", "\\\"", title)
					
					if (itemInfo):
						itemInfo = re.sub("\"", "\\\"", itemInfo)
						itemInfo = re.sub("\n", "", itemInfo)
						itemInfo = re.sub("\t", " ", itemInfo)
						itemInfo = re.sub("\r", "", itemInfo)

					if (len(itemInfo) > 0):
						itemInfo = Formatter.data(format, 'description', escape(itemInfo))[:-1]
				else:
					startTag = '<record>'
					endTag = '</record>'
					if (len(title) > 0):
						title = escape(removeNonAscii(title))
						
					if (len(url) > 0):
						url = escape(url)
					
					if (len(user) > 0):
						user = escape(user)
						
					if (len(itemInfo) > 0):
						itemInfo = Formatter.data(format, 'description', escape(itemInfo))								

				if (len(title) > 0):
					returnData += startTag + Formatter.data(format, 'title', title)

				if (len(url) > 0):
					returnData += Formatter.data(format, 'url', url) 

				if (len(score) > 0):
					returnData += Formatter.data(format, 'score', score)
					
				if (len(user) > 0):
					returnData += Formatter.data(format, 'user', user)
				
				if (len(comments) > 0):
					returnData += Formatter.data(format, 'comments', comments)

				if (len(timeAgo) > 0):
					returnData += Formatter.data(format, 'time', timeAgo)
					
				if (len(itemId) > 0):
					#cleanup
					if ('item?id=' in itemId):
						itemId = itemId.replace('item?id=', '')
					returnData += Formatter.data(format, 'item_id', itemId)

				if (len(itemInfo) > 0 ):
					returnData += itemInfo + endTag
	else:
		returnData = None
	
	return returnData

# 需要导入模块: import Formatter [as 别名]
# 或者: from Formatter import data [as 别名]
def parseCommentsContent(hnAPIUrl, hnAPIUrlBackup, apiURL, page='',format='json'):
	returnData = MutableString()
	returnData = ''
	logging.debug('HN URL: %s' % hnAPIUrl)

	result = getRemoteData(hnAPIUrl, hnAPIUrlBackup)
	if (result):
		htmlData = result.content	
		soup = BeautifulSoup(htmlData)
		urlLinksContent = soup('table')
		counter = 0
		comment_container = {}
		for node in urlLinksContent:
			commentTd = node.first('td', {'class' : 'default'})
			if (commentTd):
				authorSpan = commentTd.first('span', {'class' : 'comhead'})
				#multi-paragraph comments are a bit tricky, parser wont' retrieve them using "span class:comment" selector
				commentSpan = getParagraphCommentSiblings(commentTd.first('span', {'class' : 'comment'}))
				replyLink = commentTd.first('a', {'href' : re.compile('^reply.*')})['href']
				if (replyLink and "reply?id=" in replyLink):
					replyLink = replyLink.replace('reply?id=', '')
				if (authorSpan and commentSpan):
					#author span: <span class="comhead"><a href="user?id=dendory">dendory</a> 1 day ago  | <a href="item?id=3015166">link</a></span>
					commentId = authorSpan.first('a', {'href' : re.compile('^item.*')})
					user = authorSpan.first('a', {'href' : re.compile('^user.*')})
					#get time posted...lame but works. for some reason authorSpan.string returns NULL
					timePosted = str(authorSpan).replace('<span class="comhead">', '').replace('</span>', '')
					#now replace commentId and user blocks
					timePosted = timePosted.replace(str(user), '').replace('| ', '').replace(str(commentId), '')
					if (commentId['href'] and "item?id=" in commentId['href']):
						commentId = commentId['href'].replace('item?id=', '')
					#cleanup
					commentString = removeHtmlTags(str(commentSpan))
					if ('__BR__reply' in commentString):
						commentString = commentString.replace('__BR__reply', '')
					comment_container[counter] = [commentId, user.string, timePosted.strip(), commentString, replyLink]
					counter = counter + 1
			
		#build up string	
		commentKeyContainer = {}	
		for key in comment_container.keys():
			listCommentData = comment_container[key]
			if (listCommentData and not commentKeyContainer.has_key(listCommentData[0])):
				commentId = listCommentData[0]
				if (commentId):
					commentKeyContainer[commentId] = 1
				userName = listCommentData[1]
				whenPosted = listCommentData[2]
				commentsString = listCommentData[3]
				replyId = listCommentData[4]
				
				if (format == 'json'):
					startTag = '{'
					endTag = '},'

					#cleanup
					if (commentsString):
						commentsString = re.sub("\"", "\\\"", commentsString)
						commentsString = re.sub("\n", "", commentsString)
						commentsString = re.sub("\t", " ", commentsString)
						commentsString = re.sub("\r", "", commentsString)

					if (len(commentsString) > 0):
						commentsString = Formatter.data(format, 'comment', escape(removeNonAscii(commentsString)))
					else:
						commentsString = "n/a "
				else:
					startTag = '<record>'
					endTag = '</record>'
					if (len(userName) > 0):
						userName = escape(removeNonAscii(userName))

					if (len(whenPosted) > 0):
						whenPosted = escape(whenPosted)

					if (len(commentsString) > 0):
						commentsString = Formatter.data(format, 'comment', escape(removeNonAscii(commentsString)))								

				if (commentId and userName and whenPosted and replyId and commentsString):
					if (len(commentId) > 0):
						returnData += startTag + Formatter.data(format, 'id', commentId)
							
					if (len(userName) > 0):
						returnData += Formatter.data(format, 'username', userName)

					if (len(whenPosted) > 0):
						returnData += Formatter.data(format, 'time', whenPosted)

					if (len(replyId) > 0):
						returnData += Formatter.data(format, 'reply_id', escape(replyId))

					if (len(commentsString) > 0 ):
						returnData += commentsString + endTag
	else:
		returnData = None

	return returnData