def result():
if request.method == 'POST':
Text = request.form['Text']
article = Article()
article.addText(Text)
#article.download(Url)
#article.set_summary()
#article.set_category()
#print(article.get_thumbnailUrl())
result = {
'text': article.get_text(),
'category': article.get_category()
}
return render_template("result3.html", result=result)
def execute_with_params(self, file_pattern="", path="", magazines=None,articles=None):
listOfMagazines=[]
container = dict()
for folder, subs, files in os.walk(path):
with open(os.path.join(folder, file_pattern), 'w') as dest:
docValue=""
prevId=""
identifier=""
page_count=0
for filename in files:
#print("Filename "+filename)
if filename == file_pattern:
pass
elif filename.endswith(file_pattern):
document=""
if not folder in path:
document = folder+"/"+filename
else:
document = path+filename
doc = self.read(document)
if magazines==None:
pass
#container = self.saveValuesForNewIdentifier(container, identifier, doc)
elif len(doc)<1:
pass
else:
fileId = self.getMagazine(filename)
mag=magazines[fileId]
if fileId not in listOfMagazines:
listOfMagazines.append(fileId)
page = self.extractPageNumberFromFilename(filename)
if page > 0:
article = mag.find_article_by_page(page)
logger.debug(article)
logger.debug(filename)
#get filename
name=""
str_name = filename.split("page")
try:
name = str_name[0]
except:
name = filename
mag.set_name(name)
if article != None: #If article exists
if len(doc)<5 and len(values[-1:])<3900:
logger.info("SMALL "+str(len(doc)) + " = "+doc)
pass
if len(doc)>0:
self.setLengths(len(doc))
#split value in case too long to process
if len(doc)>3000:
sentences=""
splitted = doc.split(' ')
for split in splitted:
lenn = len(sentences) + len(split) + 1 #+1 for the space
if lenn > 3000:
article.addText(sentences, page)
sentences = ""
sentences += split+" "
if len(sentences) > 0:
article.addText(sentences, page)
else:
article.addText(doc, page)
article.set_len(len(doc))
else:
#in case we cannot find article
article = Article(filename, page, "")
article.addText(doc, page)
article.set_len(len(doc))
self.setLengths(len(doc))
mag.add_article(article)
else:
#if article not found for the document, store pages page by page
print("stored file "+filename+" as article was not found")
article = Article(filename, page, "")
article.addText(doc, page)
article.set_len(len(doc))
mag.add_article(article)
self.setLengths(len(doc))
magazines[fileId] = mag
#mag.log_articles_and_contents()
elif filename.endswith(".xml"):
page_count = 1+page_count
article = Article(filename, page, "")
doc, document = self.readDocument(path, folder, filename, document)
if len(doc)>0:
xml = xmlParser(input_file=doc)
if bool(BeautifulSoup(html, "html.parser").find()) == True:
self.setLengths(len(doc))
article.set_len(len(doc))
html = htmlParser(doc)
article = self.split_document(html.get_text(), article, page_count)
result.append(article)
else:
#process
pass
elif filename.endswith(".html"):
page_count = 1+page_count
article = Article(filename, page, "")
doc, document = self.readDocument(path, folder, filename, document)
if len(doc)>0:
self.setLengths(len(doc))
article.set_len(len(doc))
html = htmlParser(doc)
article = self.split_document(html.get_text(), article, page_count)
result.append(article)
else:
#process
pass
dest.close()
result = []
logger.debug("VALUES FOR magazines "+str(len(listOfMagazines)))
for id in listOfMagazines:
if magazines[id] not in result:
result.append(magazines[id])
return result, listOfMagazines
