def update(post: Post, post_dict: dict):
if 'date' in post_dict.keys():
post.published_at = datetime.strptime(post_dict['date'], "%Y-%m-%d")
if 'html_url' in post_dict.keys():
post.html_url = post_dict['html_url']
if 'category' in post_dict.keys():
try:
category = Category.objects.get(name=post_dict['category'])
except Category.DoesNotExist:
category = Category(name=post_dict['category'])
category.save()
post.category = category
if 'preface' in post_dict.keys():
post.preface = post_dict['preface']
if 'thumbnail' in post_dict.keys():
post.thumbnail = post_dict['thumbnail']
post.body = post_dict['body']
return post
c1 = Committee("Health Council")
c2 = Committee("Dining Council")
c3 = Committee("Education Council")
print "Adding new Category"
categories = [Category("Healthcare"),Category("Education"),Category("Tuition"),Category("Dining")]
#categories[0].committee = c1
c1.categories.append(categories[0])
#categories[1].committee = c3
c2.categories.append(categories[3])
c3.categories.append(categories[1])
c3.categories.append(categories[2])
#categories[2].committee = c3
#categories[3].committee = c2
print 'Adding new post'
post1 = Post('Terrible Dining', 'There is food poisoning epidemic because of our cafeteria food')
post1.category = categories[3]
post1.approved = True
post1.status = 'success'
post2 = Post('Need better health center', 'School needs better health services')
post2.category = categories[0]
post2.approved = True
post2.status = 'success'
post3 = Post('Tuition is too high', 'NYU needs to lower tuition')
post3.category = categories[2]
post3.approved = True
post3.status = 'success'
post4 = Post('Classes are too hard', 'Professors need to make classes easier')
post4.category = categories[1]
post5 = Post('Tuition is too cheap', 'Tuition should be higher')
post5.category = categories[2]
def make_post(bsObj):
# Iterate over the articles on the current page
for each in bsObj:
# get title
from app import db
from app.models import Post
title = each.find('div', {'class': 'content'}).h4.get_text()
# get summary
posted = Post.query.filter_by(title=title).first()
site = 'http://120.24.245.101/info/view/container/index/'
detail_url = site + each.find('h4').a.attrs['href']
# load the detail page, make page soup
detail_page = load_url(detail_url)
detail_soup = make_detail_soup(detail_page)
if posted:
# update its category
posted.category = detail_soup.find('span', {'id':'local'}).get_text()
db.session.add(posted)
db.session.commit()
else:
summary = each.p.get_text()
# get keywords
temp = []
for a in each.find('div', {'class': 'keywords'}):
temp.append(a.get_text())
# keywords should be returned as a string delimited by ,
# i.e. 'pollution, ep'
keywords = ','.join(temp)
# get external links for imgs
# add the upload feature for imgs in the future
try:
href = each.find('img').attrs['src']
except:
href = ''
# how to deal with articles that did not upload imgs
# get timestamp
timestamp = detail_soup.find('span', {'class':'article_time'}).get_text()
# 2015-07-08 14:10:40
# convert it to a datetime object, 14:10
# get body_html, preserve the tags
body_html = detail_soup.find('div', {'class':'article_detail'})
body_html = str(body_html)
# get source
source = detail_soup.find('span', {'class':'article_source'}).get_text()
category = detail_soup.find('span', {'id':'local'}).get_text()
#update model, database
# (self, title, summary, source, timestamp, keywords, img_href, body_html)
post = Post(title, summary, source, timestamp, keywords, href, body_html)
post.category = category
db.session.add(post)
db.session.commit()
