def checkAndCleanText(self, inputText, rawData):
""" Check and clean article text
"""
cleanedText = inputText
invalidFlag = False
try:
for badString in self.invalidTextStrings:
if cleanedText.find(badString) >= 0:
logger.debug(
"%s: Found invalid text strings in data extracted: %s",
self.pluginName, badString)
invalidFlag = True
# check if article content is not valid or is too little
if invalidFlag is True or len(
cleanedText) < self.minArticleLengthInChars:
cleanedText = self.extractArticleBody(rawData)
# replace repeated spaces, tabs, hyphens, '\n', '\r\n', etc.
cleanedText = filterRepeatedchars(
cleanedText,
deDupeList([' ', '\t', '\n', '\r\n', '-', '_', '.']))
cleanedText = cleanedText.replace('\n', ' ')
# remove invalid substrings:
for stringToFilter in deDupeList(self.subStringsToFilter):
cleanedText = cleanedText.replace(stringToFilter, " ")
except Exception as e:
logger.error("Error cleaning text: %s", e)
return (cleanedText)
def test_filterRepeatedchars():
# test to filter out Repeated charaters
(parentFolder, sourceFolder, testdataFolder) = getAppFolders()
sys.path.append(sourceFolder)
import scraper_utils
baseText = 'A good sentence with repeated spaces and tabs \t\t\t and\n\n\n newlines and hyphens---- dots....'
charList = [' ', '\t', '\n', '-']
resultText = scraper_utils.filterRepeatedchars(baseText, charList)
print('Result after filtering repeated characters:\n', resultText)
assert resultText == "A good sentence with repeated spaces and tabs \t and\n newlines and hyphens- dots....",\
"10. filterRepeatedchars() is not filtering repeated characters correctly."
def checkAndCleanText(self, inputText, rawData):
""" Check and clean article text
"""
cleanedText = inputText
try:
# ignore the newspaper extracted text, the alternate method text is more accurate:
cleanedText = self.extractArticleBody(rawData)
for badString in self.invalidTextStrings:
if cleanedText.find(badString) >= 0:
logger.debug("%s: Found invalid text strings in data extracted: %s", self.pluginName, badString)
return(None)
# replace repeated spaces, tabs, hyphens, '\n', '\r\n', etc.
cleanedText = filterRepeatedchars(cleanedText,
deDupeList([' ', '\t', '\n', '\r\n', '-', '_', '.']))
# remove invalid substrings:
for stringToFilter in deDupeList(self.subStringsToFilter):
cleanedText = cleanedText.replace(stringToFilter, " ")
except Exception as e:
logger.error("Error cleaning text: %s", e)
return(cleanedText)
