def test_add(self):
# Create an Article.
a5 = Article(id=None, headline='Django lets you reate Web apps easily')
# You can't associate it with a Publication until it's been saved.
self.assertRaises(ValueError, getattr, a5, 'publications')
# Save it!
a5.save()
# Associate the Article with a Publication.
a5.publications.add(self.p1)
self.assertQuerysetEqual(a5.publications.all(),
['<Publication: The Python Journal>'])
# Create another Article, and set it to appear in both Publications.
a6 = Article(id=None, headline='ESA uses Python')
a6.save()
a6.publications.add(self.p1, self.p2)
a6.publications.add(self.p3)
# Adding a second time is OK
a6.publications.add(self.p3)
self.assertQuerysetEqual(a6.publications.all(), [
'<Publication: Science News>',
'<Publication: Science Weekly>',
'<Publication: The Python Journal>',
])
# Adding an object of the wrong type raises TypeError
self.assertRaises(TypeError, a6.publications.add, a5)
# Add a Publication directly via publications.add by using keyword arguments.
p4 = a6.publications.create(title='Highlights for Adults')
self.assertQuerysetEqual(a6.publications.all(), [
'<Publication: Highlights for Adults>',
'<Publication: Science News>',
'<Publication: Science Weekly>',
'<Publication: The Python Journal>',
])
def newarticle(request):
if not request.user.is_authenticated():
return redirect('/Login/?next=%s' % request.path)
if request.method=='POST':
title=request.POST['title']
tags=request.POST['tag']
cat=request.POST['cat']
content=request.POST['content']
tags=tags.split(',')
tagm=[]
print tags
for i in tags:
a=Tag.objects.filter(tag=i)
if a:
tagm.append(a[0])
else:
t=Tag(tag=i)
t.save()
tagm.append(t)
if cat.find('mc')>0:
maincat=MainCat.objects.get(id=cat[:cat.find('m')])
ar=Article(user=request.user,title=title,content=content,maincat=maincat)
elif cat.find('-')==-1:
dcat=DetailCat.objects.get(id=cat)
maincat=dcat.maincat
ar=Article(user=request.user,title=title,content=content,detailcat=dcat,maincat=maincat)
else:
ar=Article(user=request.user,title=title,content=content)
ar.save()
ar.tag=tagm
ar.save()
return redirect(getarticle,ar.id)
maincat=MainCat.objects.all()
nart,cart,rart,cm,tg=getthree()
#日历
today=today=datetime.datetime.now()
s=calendar.HTMLCalendar(6)
cals=list(s.itermonthdays2(today.year,today.month))
tdarts=Article.objects.values('id','createtime').filter(createtime__year=today.year,createtime__month=today.month).order_by('createtime') #列表字典[{'createtime': datetime.datetime(2014, 4, 6, 4, 36, 32, 896000, tzinfo=<UTC>)},
tdart=set([i['createtime'].day for i in tdarts])
tmpq=Article.objects.exclude(createtime__year=today.year,createtime__month=today.month)
premon=tmpq.filter(createtime__lt=today).order_by('-createtime')[:1]
aftmon=tmpq.filter(createtime__gt=today).order_by('createtime')[:1]
tt=[]
for i in cals:
tt.append(list(i))
ttt=[]
for a in tt:
for i in tdart:
if a[0] == i:
a.append(1)
if len(a)==2:
a.append(0)
ttt.append(a)
return render_to_response('new.htm',locals(),context_instance=RequestContext(request))
def post(self):
"""Edit Artilce."""
data = self.request.data(title='', tag='', category='', \
raw_content='', old_tag='', created_at='')
created_at = data.created_at
title = data.title
old_tag = data.old_tag
tag = data.tag
category = data.category
raw_content = data.raw_content
content = (markdown2.markdown(raw_content)).encode('utf-8')
u_id = self.get_current_user()
admin = User.get_by_primary_key(u_id)
created_at_now = int(time.time())
# new article
if not created_at:
article = Article(title=title,content=content,\
raw_content=raw_content,category=category, \
author=admin.name, created_at=created_at_now)
article.insert()
new_article = Article.select_one('created_at=?', created_at_now)
article_id = new_article.id
# tag
tag_d = Tag.select_one('tag_name=?', tag)
# tag doesn't exists
if not tag_d:
new_tag = Tag(tag_name=tag)
new_tag.insert()
get_tag = Tag.select_one('tag_name=?', tag)
tag_id = get_tag.id
# tag exists
else:
tag_id = tag_d.id
article_tag = ArticleTag(article_id=article_id, tag_id=tag_id)
article_tag.insert()
# update old article
else:
article = Article(title=title, content=content, \
raw_content=raw_content, author=admin.name, \
category=category, created_at=created_at_now)
article.update('created_at=?', created_at)
new_article = Article.select_one('created_at=?', created_at_now)
article_id = new_article.id
old_tag = Tag.select_one('tag_name=?', old_tag)
new_tag = Tag(tag_name=tag)
other_article_tag = ArticleTag.select_all('tag_id=?', old_tag.id)
# other article doesn't have this article
if len(other_article_tag) >= 1:
tag_id = old_tag.id
new_tag.update('id=?', tag_id)
# other article has this tag
else:
new_tag.insert()
get_tag = Tag.select('tag_name=?', tag)
tag_id = get_tag.id
article_tag = ArticleTag(tag_id=tag_id)
article_tag.update('article_id=?', article_id)
self.redirect('/admin/articles')
def test_create(self):
# You can also instantiate an Article by passing the Reporter's ID
# instead of a Reporter object.
a3 = Article(id=None, headline="Third article",
pub_date=datetime(2005, 7, 27), reporter_id=self.r.id)
a3.save()
self.assertEqual(a3.reporter.id, self.r.id)
# Similarly, the reporter ID can be a string.
a4 = Article(id=None, headline="Fourth article",
pub_date=datetime(2005, 7, 27), reporter_id=str(self.r.id))
a4.save()
self.assertEqual(repr(a4.reporter), "<Reporter: John Smith>")
def getArticles():
articles = Article.query()
if articles.count() == 0:
hello = Article()
hello.title = "Hello World"
hello.content = "Lorem ipsum dolor sit amet, consectetur adipisicing elit. Consequuntur, voluptatum. Provident accusamus sit, commodi corrupti illo, veniam possimus minima rerum itaque. Magni, beatae, facere."
hello.put()
bye = Article()
bye.title = "Bye World"
bye.content = "Iraqi PM Nouri Maliki steps aside, ending political deadlock in Baghdad as the government struggles against insurgents in the north."
bye.put()
del hello, bye
articles = Article.query()
return serialize(list(articles.order(Article.date).fetch(10)))
def setUp(self):
# Create a Reporter.
self.r = Reporter(name='John Smith')
self.r.save()
# Create an Article.
self.a = Article(headline="First", reporter=self.r)
self.a.save()
# Create an Article via the Reporter object.
self.a2 = self.r.article_set.create(headline="Second")
# Create an Article with no Reporter by passing "reporter=None".
self.a3 = Article(headline="Third", reporter=None)
self.a3.save()
# Create another article and reporter
self.r2 = Reporter(name='Paul Jones')
self.r2.save()
self.a4 = self.r2.article_set.create(headline='Fourth')
def art_add():
form = ArticleAddForm()
if form.validate_on_submit():
data = form.data
# 上传logo
file = secure_filename(form.logo.data.filename) #编译安全文件名称
logo = change_name(file)
if not os.path.exists(app.config["uploads"]):
os.makedirs(app.config["uploads"])
# 保存文件
form.logo.data.save(app.config["uploads"] + "/" + logo)
# 获取用户ID
user = User.query.filter_by(account=session["user"]).first()
user_id = user.id
# 保存数据，Article
article = Article(
title=data["title"],
category=data["category"],
user_id=user_id,
logo=logo,
content=data["content"],
add_time=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
)
db.session.add(article)
db.session.commit()
flash(u"发布文章成功", "ok")
return render_template("art_add.html", title="发布文章", form=form)
def art_add():
articleform=ArticleForm()
if articleform.validate_on_submit():
data=articleform.data
#update picture
datas=secure_filename(articleform.logo.data.filename)
logo=change_filename(datas)
if not os.path.exists(app.config["UP"]):
os.makedirs(app.config["UP"])
#save file
articleform.logo.data.save(app.config["UP"]+"/"+logo)
#get userID
user=User.query.filter_by(username=session["user"]).first()
user_id=user.id
#save data
articale =Article(
title=data["title"],
category=data["category"],
user_id=user_id,
logo=logo,
content=data["content"],
addTime=datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
)
db.session.add(articale)
db.session.commit()
flash(u"Add review successfully!","ok")
return render_template("artadd.html",form=articleform)
def article_edit():
if request.method == 'GET':
artic_id = request.args.get('artic_id')
tag_all = Material.query.with_entities(Material.tag.distinct().label("tag")).filter(Material.user_id==session['user_id'])
if artic_id:
article = Article.query.filter(Article.artic_id==int(artic_id),Article.user_id==session['user_id']).first()
return render_template('article_edit.html', article=article,tags=tag_all)
else:
return render_template('article_edit.html',tags=tag_all)
else:
artic_id = request.form['artic_id']
title = request.form['title']
content = request.form['content']
edit_time = datetime.utcnow()
user_id = session['user_id']
# print(mater_id,title,content,edit_time,user_id)
if artic_id:
article = Article.query.filter(Article.artic_id==int(artic_id),Article.user_id==session['user_id']).first()
article.title = title
article.content = content
article.edit_time = edit_time
db.session.add(article)
db.session.commit()
else:
article = Article(title=title,content=content,user_id=user_id,edit_time=edit_time)
db.session.add(article)
db.session.commit()
# return u"提交成功"
return redirect(url_for('index'))
def test_country_4(self):
c = Country(name='Cowland')
a = Article(title='President Cowy McMoo to Ban Strawberry Milk')
c.articles.append(a)
db.session.add(c)
first = Country.query.first()
self.assertEqual(len(first.articles), 1)
def save(self, username,article=None):
cd = self.cleaned_data
title = cd['title']
title_zh = title
now = datetime.datetime.now()
content_md = markdown.markdown(cd['content'])
url = '/article/%s' % (title)
tags = cd['tags']
if article:
article.URL=url
article.title=title
article.title_zh=title_zh
article.content=content_md
article.tags=tags
article.updated=now
else:
article = Article(
URL=url,
title=title,
title_zh=title_zh,
author=username,
content=content_md,
tags=tags,
views=0,
created=now,
updated=now
)
article.save()
def to_Article(self):
return Article(title=self.title.data,
author=self.author.data,
highlight=self.highlight.data,
subject=self.subject.data,
date=datetime.datetime.now(),
email=self.email.data)
def update_articles(data):
source_id = data['source_id'] or 'NA'
author = data['author']
title = data['title']
description = data['description']
url = data['url']
img_url = data['img_url']
published_at = data['published_at']
content = data['content']
boards = data['board_id']
article = Article(source_id=source_id,
author=author,
title=title,
description=description,
url=url,
img_url=img_url,
published_at=published_at,
content=content)
db.session.add(article)
db.session.commit()
for board in boards:
board_id = board
article_id = article.id
article_board = ArticleBoard(board_id=board_id, article_id=article_id)
db.session.add(article_board)
db.session.commit()
return
def parse(self, response):
# grab list of article URLs on the page
urls = response.xpath(
'//*[@id="content_wrapper"]/div/div[2]/div[2]/div[2]/ul/*/div/a/@href'
).extract()
for url in urls:
# make URL requestable
full_url = self.base_url + url
article_id = int(url.split('/')[2].split('-')[0])
# check if URL is in the database
if db.session.query(Article).get(article_id) is not None:
print('Article {} is already in the database, pass.'.format(
str(article_id)))
pass
# add it to the database if the article_id is not in already
else:
article = {}
article['article_id'] = int(article_id)
article['article_url'] = full_url
db.session.add(Article(**article))
db.session.commit()
print('Article {} has been added to the database.'.format(
str(article_id)))
def api_data_api():
data = request.get_json()
msg = data.get('message')
if msg != "success":
return wrap_false(msg="获取数据错误")
article_list = data.get('data')
count = len(article_list)
if count == 0:
return wrap_false(msg="获取到的数据为空")
allow_num = 0
for article in article_list:
if Article(article).pop():
allow_num += 1
print('符合筛选要求,成功添加')
else:
print('未符合筛选要求')
print("allow_num:{},count:{}".format(allow_num, count))
point = allow_num / count
print('总共：{} 成功{} 成功率{}'.format(count, allow_num, point))
if point < 0.5:
data = {"status": "end"}
return wrap_true(msg="上传成功", data=data)
data = {
"status": "keep",
"max_behot_time": data.get('next').get('max_behot_time')
}
return wrap_true(msg="继续上传", data=data)
def create_article(request, block_id):
block_id = int(block_id)
block = Block.objects.get(id=block_id) # get方法要求只返回一个结果
if request.method == "GET":
return render_to_response("article_create.html", {"b": block},
context_instance=RequestContext(request))
else: # POST
title = request.POST["title"].strip()
content = request.POST["content"].strip()
if not title or not content:
# pass
messages.add_message(request, messages.ERROR, u'标题和内容不允许为空')
return render_to_response(
"article_create.html",
# {"b": block, "title": title, "content": content},#可以不需要这些参数只为传入到html时候用的
context_instance=RequestContext(request)) # 停留在当前页面
else:
owner = User.objects.all()[0] # TODO
news_article = Article(block=block,
owner=request.user,
content=content,
title=title)
news_article.save()
messages.add_message(request, messages.INFO, u'文章发布成功')
return redirect(reverse("article_list", args=[
block.id
])) # 根据url名称反查url地址(返回一个字符串) 等同于html {% url 'URL名称' 位置参数 关键字参数 %}
def article_post():
form = set_article_form()
if form.validate_on_submit():
cate_id = form.data['cate']
title = form.data['title']
thumb = form.data['thumb']
intro = form.data['intro']
content = form.data['content']
article = Article(
cate_id=cate_id,
title=title,
thumb=thumb,
intro=intro,
content=content,
author=session['user']
)
try:
db.session.add(article)
db.session.commit()
except Exception as e:
print(str(e))
message = {'message': '文章发布失败'}
else:
message = {"message": "文章发布成功"}
return jsonify(message)
return render_template("member/article/article_post.html", form=form)
def add_art():
if account() < 0:
if request.method == 'POST':
cate_id = request.form.get('cate_id')
art_name = request.form.get('art_name')
describe = request.form.get('describe')
content = request.form.get('content')
article = Article(cate_id=cate_id,
art_name=art_name,
describe=describe,
content=content,
author=session.get('user_id'))
db.session.add(article)
db.session.commit()
return 'ok'
else:
cate = []
categories = Category.query.all()
for c in categories:
if c.parent_id == 0:
c.cate_name = '|--' + c.cate_name
cate.append(c)
for s in categories:
if s.parent_id == c.id:
s.cate_name = '|------' + s.cate_name
cate.append(s)
return render_template('admin/add_art.html', cate=cate)
else:
return redirect(url_for('login'))
def new_article():
""" add new article """
if not authenticated():
return redirect(url_for('login'))
if request.method == 'GET':
topics, _articles = base_query(db_session)
return render_template('article_form.html',
is_authenticated=authenticated,
topics=topics,
article=None,
action='new')
else:
form = dict(request.form)
article = Article(title=form['article_title'][0],
url=form['article_url'][0],
date_added=date.today(),
description=form['article_description'][0],
topic_id=form['article_topic_id'][0],
adder_id=session['user_id'])
db_session.add(article)
db_session.commit()
return redirect(url_for('index'))
def run(self):
try:
urls_article = [
'https://mp.weixin.qq.com/s?src=11×tamp=1541559601&ver=1229&signature=ixTsG-RvK8H58t6D-CpW6olWI8hA52Wz-FRb12ZcrNG-lxR20YutoyLYUr-RB3w8WHjE1petjDcbbxZVxTChvPWM27qszWu0Z3zonjx8SEQB5mmgm1O9Eu*5qsFhnBCH&new=1'
]
entity = None
backpack_list = []
ftp_list = []
ftp_info = None
for page_count, url in enumerate(urls_article):
# if page_count < 15:
# continue
html = requests.get(url)
# 确定account信息
name = pq(html.text)('#js_name').text()
account_name = pq(
html.text)('.profile_meta_value').eq(0).text()
log('---{}---{}---'.format(name, account_name))
account = Account()
account.name = name
account.account = account_name
account.get_account_id()
article = Article()
try:
article.create(url, account)
except RuntimeError as run_error:
log('找不到浏览器 {}'.format(run_error))
log('第{}条 文章标题: {}'.format(page_count, article.title))
log("当前文章url: {}".format(url))
entity = JsonEntity(article, account)
log('当前文章ID: {}'.format(entity.id))
# if entity.id in ids:
# log('当前文章已存在，跳过')
# continue
backpack = Backpack()
backpack.create(entity)
backpack_list.append(backpack.create_backpack())
# self.save_to_mysql(entity)
self.save_to_mongo(entity.to_dict())
# ftp包
ftp_info = Ftp(entity)
name_xml = ftp_info.hash_md5(ftp_info.url)
log('当前文章xml: {}'.format(name_xml))
self.create_xml(ftp_info.ftp_dict(), name_xml)
ftp_list.append(name_xml)
# if page_count >= 3:
# break
log("发包")
# todo 发包超时，修改MTU
if ftp_info is not None:
entity.uploads_ftp(ftp_info, ftp_list)
if entity:
# entity.uploads(backpack_list)
entity.uploads_datacenter_relay(backpack_list)
entity.uploads_datacenter_unity(backpack_list)
log("发包完成")
except Exception as e:
log("解析公众号错误 {}".format(e))
if 'chrome not reachable' in str(e):
raise RuntimeError('chrome not reachable')
def frontpage_cms_new():
page = 'CMS'
if request.method == "POST":
title = request.json['articleTitle']
category = request.json['articleCategory']
summary = request.json['articleSummary']
content = request.json['articleContent']
status = request.json['articleStatus']
if status == 'Published':
published_date = datetime.date.today()
added_date = datetime.date.today()
elif status == 'Draft':
published_date = None
added_date = datetime.date.today()
article = Article(title=title,
content=content,
author_id=current_user.id,
category=category,
published_date=published_date,
added_date=added_date,
summary=summary,
status=status)
db.session.add(article)
db.session.commit()
return jsonify(**request.json)
else:
return render_template('employee_site/front-page/new_article.html',
page=page)
def test_add(self):
# Create an Article via the Reporter object.
new_article = self.r.article_set.create(headline="John's second story",
pub_date=datetime(2005, 7, 29))
self.assertEqual(repr(new_article), "<Article: John's second story>")
self.assertEqual(new_article.reporter.id, self.r.id)
# Create a new article, and add it to the article set.
new_article2 = Article(headline="Paul's story",
pub_date=datetime(2006, 1, 17))
self.r.article_set.add(new_article2)
self.assertEqual(new_article2.reporter.id, self.r.id)
self.assertQuerysetEqual(self.r.article_set.all(), [
"<Article: John's second story>",
"<Article: Paul's story>",
"<Article: This is a test>",
])
# Add the same article to a different article set - check that it moves.
self.r2.article_set.add(new_article2)
self.assertEqual(new_article2.reporter.id, self.r2.id)
self.assertQuerysetEqual(self.r2.article_set.all(),
["<Article: Paul's story>"])
# Adding an object of the wrong type raises TypeError.
self.assertRaises(TypeError, self.r.article_set.add, self.r2)
self.assertQuerysetEqual(self.r.article_set.all(), [
"<Article: John's second story>",
"<Article: This is a test>",
])
def setup(self):
"""
Set up method that will run before every Test
"""
self.new_article = Article("nana", "TestTitle", "TestDescription",
"TestUrl", "TestUrlToImage",
"TestPublishedAt", "TestContent")
def parseAndStoreDoc(self):
for e in self.doc.entries:
title = jinja2.Markup(e.title).unescape()
link = e.links[0]["href"]
soup = BeautifulSoup(e.description)
try:
description = jinja2.Markup(soup.findAll("p")[-1]).unescape()
except IndexError as e:
description = jinja2.Markup(soup).unescape()
# try:
# imgLink = soup.findAll("img")[0]["src"]
# except IndexError as e:
imgLink = GQ.gqLogo
srcName = self.srcName
labelName = self.srcName.split("_")[1]
article = Article(title=title,
description=description,
imgLink=imgLink,
link=link,
srcName=srcName,
labelName=labelName)
article.put()
logging.info("Storing data from %s" % srcName)
def editor(article_id):
if request.method == 'POST':
title = request.form.get("title")
content = request.form.get("content")
filename = None
if 'main_image' in request.files:
file = request.files['main_image']
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
if article_id:
article = Article.get(article_id)
if filename: #change filename only if new file uploaded
article.edit(article_id,
title=title,
content=content,
main_image=filename)
else:
article.edit(article_id, title=title, content=content)
return redirect('/editor')
else:
article = Article(title=title,
content=content,
main_image=filename)
article.create()
return redirect('/editor')
articles = Article.fetch()
if article_id:
article = Article.get(article_id)
else:
article = None
return render_template('editor.html', articles=articles, article=article)
def parseAndStoreDoc(self):
for e in self.doc.entries:
title = jinja2.Markup(e.title).unescape()
soup = BeautifulSoup(e.description)
description = jinja2.Markup(soup.getText()).unescape()
#truncate the length of
if len(description) > 500:
description = description[:500]
link = e.links[0]["href"]
srcName = self.srcName
labelName = self.srcName.split("_")[1]
# if no image in entry, use the source logo instead
try:
imgLink = e.media_content[0]["url"]
except AttributeError as e:
imgLink = NewYorkTimes.logo
article = Article(title=title,
description=description,
imgLink=imgLink,
link=link,
srcName=srcName,
labelName=labelName)
article.put()
logging.info("Storing data to database!(from %s)" % srcName)
def post(self, request, *args, **kwargs):
if request.session.get('account_id', None) is None:
return HttpResponseRedirect('/account/login')
try:
article_id = kwargs['id']
d = request.POST.dict()
i = Article.objects.get(id=article_id)
tag = d.get('tag', '')
if tag != '':
if tag[-1] == ';':
tag = tag[:-1]
i.tag = tag.split(';')
i.category = int(d['category'])
i.head_image = d.get('head_image', None)
i.title = d['title']
i.content = d['content']
i.status = 0
i.save()
except:
d = request.POST.dict()
i = Article(**d)
account_id = request.session['account_id']
i.account_id = str(account_id)
i.username = request.session['username']
tag = d.get('tag', None)
if tag != '':
if tag[-1] == ';':
tag = tag[:-1]
i.tag = tag.split(';')
i.status = 0
i.save()
return HttpResponse(i.id)
def save(self, username, article=None):
cd = self.cleaned_data
title = cd['title']
title_zh = title
now = datetime.datetime.now()
content_md = cd['content']
content_html = markdown.markdown(cd['content'])
re_title = '<h\d>(.+)</h\d'
data = content_html.split('\n')
for line in data:
title_info = re.findall(re_title, line)
if title_info:
title_zh = title_info[0]
break
url = '/article/%s' % (title)
tags = cd['tags']
article = Article(
url=url,
title=title,
title_zh=title_zh,
author=username,
content_md=content_md,
content_html=content_html,
tags=tags,
views=0,
created=now,
updated=now,
)
article.save()
def test_reverse_add(self):
# Adding via the 'other' end of an m2m
a5 = Article(headline='NASA finds intelligent life on Mars')
a5.save()
self.p2.article_set.add(a5)
self.assertQuerysetEqual(self.p2.article_set.all(), [
'<Article: NASA finds intelligent life on Earth>',
'<Article: NASA finds intelligent life on Mars>',
'<Article: NASA uses Python>',
'<Article: Oxygen-free diet works wonders>',
])
self.assertQuerysetEqual(a5.publications.all(),
['<Publication: Science News>'])
# Adding via the other end using keywords
new_article = self.p2.article_set.create(
headline='Carbon-free diet works wonders')
self.assertQuerysetEqual(self.p2.article_set.all(), [
'<Article: Carbon-free diet works wonders>',
'<Article: NASA finds intelligent life on Earth>',
'<Article: NASA finds intelligent life on Mars>',
'<Article: NASA uses Python>',
'<Article: Oxygen-free diet works wonders>',
])
a6 = self.p2.article_set.all()[3]
self.assertQuerysetEqual(a6.publications.all(), [
'<Publication: Highlights for Children>',
'<Publication: Science News>',
'<Publication: Science Weekly>',
'<Publication: The Python Journal>',
])
def scrape_homepage(self, **kwargs):
"""
Scrape!
"""
logger.info('Scraping homepage (start time: %s)' % self.run_time)
if not kwargs:
response = requests.get(self.url)
page = PyQuery(response.content)
else:
page = PyQuery(**kwargs)
article_elements = page('.stories-wrap article')
slot = 0
articles = []
for el in article_elements:
element = PyQuery(el)
article = Article(element, self.run_time)
if not article.story_id and not article.is_apps_project:
continue
if not element.hasClass('attachment'):
slot += 1
article.slot = slot
articles.append(article)
logger.info('Scraped %s from homepage (%s)' %
(article.story_id, article.headline))
return articles
