def formdata(links):
data=[]
for i in links:
try:
html=requests.get(i).text
soup=sp(html,'lxml')
url=i
title=soup.find('title').text
tag=''
category=''
try:
tag=getTagAndCateByLink(i,'Tags')
except Exception:
pass
try:
category=getTagAndCateByLink(i,'Categories')
except Exception:
pass
try:
catchhtml=soup.find(id='cnblogs_post_body')
catchhtml=str(catchhtml)
data.append(article(url, title, catchhtml,tag,category))
except Exception:
print(i+' has no main')
except Exception as e:
print e
return data
def success_page(request):
ai = request.session.get("author_id")
aname = request.session.get("author_name")
aemail = request.session.get("author_email")
a = author_signup(aid=ai, author_name=aname, email=aemail)
at = article(uid=a, title=request.POST["title"], content=request.POST["content"], pub_date=timezone.now())
at.save()
return render(request, "success.html", {"art": at})
def AddTextFileToDB(filename):
with open(filename, "r") as textfile:
url = textfile.readline()
date = textfile.readline()
score = textfile.readline()
magnitude = textfile.readline()
article_content = textfile.read()
article_file = article(title=url,date=date,score=score, magnitude=magnitude, article_content=article_content)
article_file.save()
def setUp(self):
'''
Set up method that will run before every Test
'''
self.new_article = article(
'null', 'Forbes.com', 'Billy Bambrough, Contributor',
'Twitter CEO Jack Dorsey Has Made A Bold Prediction About Bitcoin',
'https://www.forbes.com/sites/billybambrough/2019/02/04/twitter-ceo-jack-dorsey-has-made-a-bold-prediction-about-bitcoin/',
'2019-02-04T06:10:00Z')
def getDocList(file):
doclist=[];
r=re.compile("标 题:")
b=re.compile(" ")
c="first";
art= article()
art.title=c
art.text=""
for line in file.readlines():
m=r.match(line)
if m :
print line+",,,,,,,,,,,,,,,,,,,,,,"
z= r.sub("",line)
c=b.sub("",z)
doclist.append(art);
art=article()
art.title=c
art.text=""
else:
line=b.sub("",line)
art.text=art.text+line
doclist.append(art);
return doclist
def getDocList(file):
doclist = []
r = re.compile("标 题:")
b = re.compile(" ")
c = "first"
art = article()
art.title = c
art.text = ""
for line in file.readlines():
m = r.match(line)
if m:
print line + ",,,,,,,,,,,,,,,,,,,,,,"
z = r.sub("", line)
c = b.sub("", z)
doclist.append(art)
art = article()
art.title = c
art.text = ""
else:
line = b.sub("", line)
art.text = art.text + line
doclist.append(art)
return doclist
def post(self, request):
form = articleForm(request.POST)
if form.is_valid(): # 验证数据是否合法
url = "".join([reverse('djManage'), "/article"])
newTitle = form.cleaned_data['title']
newBody = form.cleaned_data['body']
if form.cleaned_data['abstract'] is None:
newAbstract = newBody[:200]
else:
newAbstract = form.cleaned_data['abstract']
newAbstract.replace('\s', '')
newArticle = article(title=newTitle,
body=newBody,
abstract=newAbstract)
print newArticle.body
newArticle.save()
return HttpResponseRedirect(url)