def getMDAfromText(filename,text):
try:
soup = BeautifulSoup(text, "lxml")
fullText = scraper.scrapeByAnchorTag(soup)
if fullText is not None:
print("{0}\tScraped By Anchor".format(filename))
return fullText
fullText = scraper.scrapeByRegex(soup)
if fullText is not None:
print("{0}\tScraped By Regex".format(filename))
return fullText
if fullText is None:
print("{0}\tUnable to scrape".format(filename))
text = ''.join(soup.findAll(text=True))
text.replace("’","'")
helper.writeToDirectoryFile("debug",filename,text)
return None
except UnicodeEncodeError:
print("{0}\tUnicodeEncodeError".format(filename))
helper.writeToDirectoryFile("debug",filename,text)
return None
