Definition at line 21 of file alchemy_extractor.py.
◆ __init__()
def dc_processor.alchemy_extractor.AlchemyExtractor.__init__ |
( |
|
self, |
|
|
|
config, |
|
|
|
templ = None , |
|
|
|
domain = None , |
|
|
|
processorProperties = None |
|
) |
| |
Definition at line 24 of file alchemy_extractor.py.
24 def __init__(self, config, templ=None, domain=None, processorProperties=None):
25 BaseExtractor.__init__(self, config, templ, domain, processorProperties)
26 self.name = CONSTS.EXTRACTOR_NAME_ALCHEMY
27 self.data[
"extractor"] = CONSTS.EXTRACTOR_NAME_ALCHEMY
28 logger.debug(
"Properties: %s",
varDump(self.properties))
31 self.rankReading(self.__class__.__name__)
def varDump(obj, stringify=True, strTypeMaxLen=256, strTypeCutSuffix='...', stringifyType=1, ignoreErrors=False, objectsHash=None, depth=0, indent=2, ensure_ascii=False, maxDepth=10)
def __init__(self)
constructor
◆ extractTags()
def dc_processor.alchemy_extractor.AlchemyExtractor.extractTags |
( |
|
self, |
|
|
|
resource, |
|
|
|
reslt |
|
) |
| |
Definition at line 34 of file alchemy_extractor.py.
34 def extractTags(self, resource, reslt):
36 logger.info(
"AAAAAAA")
38 logger.info(
"BBBBBBB")
39 text = parser.text(
"html", resource.raw_html)
40 logger.info(
"CCCCCCC")
41 logger.info(
"Article's corpus: %s", text)
42 self.addTag(result=reslt, \
43 tag_name=CONSTS.TAG_CONTENT_UTF8_ENCODED, \
45 logger.info(
"DDDDDDD")
46 except Exception, err:
51 def varDump(obj, stringify=True, strTypeMaxLen=256, strTypeCutSuffix='...', stringifyType=1, ignoreErrors=False, objectsHash=None, depth=0, indent=2, ensure_ascii=False, maxDepth=10)
◆ name
dc_processor.alchemy_extractor.AlchemyExtractor.name |
The documentation for this class was generated from the following file: