class ExtractionListAPI(Resource):
#curl http://localhost:5000/extractions
#curl http://localhost:5000/extractions?"<page_id>"
def get(self): # returns all Extractions, or returns a specific Extractions based on page_id
args = parser.parse_args()
page_id = args['page_id']
if page_id is None or "": # requested all Extractions
jsonify = lambda x: x._to_json(x.id) if x else {}
return map(jsonify, Extraction.get_all_extractions())
else: # requested Extractions filtered by one page_id
retval = lambda x: x._to_json(x.id) if x else 400
return retval(Extraction.get_extraction_by_page_id(page_id))
# curl http://localhost:5000/pages -d "url=http://www.bbc.com" -X POST -v
def post(self): # creates a new page
args = parser.parse_args()
page_id = args['page_id']
if page_id is None or "":
return 400 # bad request
retval = lambda x: x._to_json(x.id) if x else 400
return retval(Extraction.add_extraction(page_id))
manager.add_document(Extraction)
manager.add_viewdef(Extraction.all_extractions)
manager.add_viewdef(Extraction.extraction_by_page_id)
manager.sync(app)
api.add_resource(ExtractionAPI, '/extractions/<string:_id>')
api.add_resource(ExtractionListAPI, '/extractions')
@staticmethod
def get_by_domain(protocol, domain):
r = RobotsTxt.robtxt_by_domian(key=[protocol, domain])
if len(r) > 0:
# we have already crawled here and obtained RobotsTxt info. No need to request it again
for row in r:
doc = RobotsTxt.load(row.value)
if doc.is_valid():
return doc
else:
# We are here for the first time, we need to get the RobotsTxt info and store it for current and future reference
doc = RobotsTxt(protocol=protocol, domain=domain)
doc.update()
return doc
manager.add_document(Page)
manager.add_viewdef(Page.all_pages)
manager.add_viewdef(Page.page_by_url)
manager.add_document(RobotsTxt)
manager.add_viewdef(RobotsTxt.robtxt_by_domian)
manager.sync(app)
api.add_resource(PageAPI, '/pages/<string:_id>')
api.add_resource(PageListAPI, '/pages')
########### Helper functions #######
def unescape(text):
"""Removes HTML or XML character references and entities from a text string.
keep &, >, < in the source code.
"""
def fixup(m):