def run_step(self, prev, params):
# read data
hs2 = pd.read_excel(prev, sheet_name='hs2')
hs4 = pd.read_excel(prev, sheet_name='hs4')
hs6 = pd.read_excel(prev, sheet_name='hs6')
chapter = pd.read_excel(prev, sheet_name='chapter')
ran = {'hs2': 4,
'hs4': 6,
'chapter': 2}
langs = ['es', 'en']
for k, v in ran.items():
ids = hs6['id'].astype('str').str.zfill(8).str[:v].astype('int')
hs6['{}_id'.format(k)] = ids
for lan in langs:
hs6['{}_{}'.format(k, lan)] = ids
hs6['{}_{}_short'.format(k, lan)] = ids
ran = {'hs2': hs2,
'hs4': hs4,
'hs6': hs6,
'chapter': chapter}
for k, v in ran.items():
for lan in langs:
target = '{}_{}_short'.format(k, lan)
base = '{}_{}'.format(k, lan)
v = fill_values(v, target, base)
for k, v in ran.items():
for lan in langs:
target = '{}_{}_short'.format(k, lan)
base = '{}_{}'.format(k, lan)
hs6[target].replace(dict(zip(v['id'], v[target])), inplace=True)
hs6[base].replace(dict(zip(v['id'], v[base])), inplace=True)
hs6.drop(columns=['trade_value'], inplace=True)
hs6.rename(columns={'id': 'hs6_id',
'chapter_id': 'chapter'}, inplace=True)
hs6.sort_values(by='hs6_id', inplace=True)
cols_es = ['chapter_es', 'chapter_es_short', 'hs2_es', 'hs2_es_short', 'hs4_es', 'hs4_es_short', 'hs6_es', 'hs6_es_short']
cols_en = ['chapter_en', 'chapter_en_short', 'hs2_en', 'hs2_en_short', 'hs4_en', 'hs4_en_short', 'hs6_en', 'hs6_en_short']
# codes ids
nltk.download('stopwords')
stopwords_es = nltk.corpus.stopwords.words('spanish')
hs6 = format_text(hs6, cols_es, stopwords=stopwords_es)
hs6 = format_text(hs6, cols_en, stopwords=stop_words.ENGLISH_STOP_WORDS)
for col in ['hs6_id', 'hs4_id', 'hs2_id', 'chapter']:
hs6[col] = hs6[col].astype('int')
hs6.drop_duplicates(subset='hs6_id', inplace=True)
return hs6
def __create_preview(review):
preview = ''
if review.get('review'):
if review['review']['containsSpoilers']:
preview += '```This review may contain spoilers.```'
else:
preview += format_text(review['review']['lbml'], 400)
return preview
def post(self, pid):
name = self.get_argument("reply[name]", default='')
email = self.get_argument("reply[email]", default='')
website = self.get_argument("reply[website]", default='')
origin_content = self.get_argument("reply[content]", default='')
content = format_text(md(format_text(origin_content)))
if name == "":
self.redirect("/post/%d" % int(pid), error=u"请填入名字")
if email == "":
self.redirect("/post/%d" % int(pid), error=u"请填入邮箱地址")
if origin_content == "":
self.redirect("/post/%d" % int(pid), error=u"请输入评论内容")
number = db.query(Reply).filter(Reply.pid == pid).count() + 1
db.add(Reply(pid=int(pid), name=name, email=email, website=website,
content=content, origin_content=origin_content, number=number))
db.commit()
self.set_replyer(name, email, website)
self.redirect("/post/%d#%d" % (int(pid), int(number)))
def post(self, pid):
name = self.get_argument("reply[name]", default='')
email = self.get_argument("reply[email]", default='')
website = self.get_argument("reply[website]", default='')
origin_content = self.get_argument("reply[content]", default='')
content = format_text(md(format_text(origin_content)))
if name == "":
self.redirect("/post/%d" % int(pid), error=u"请填入名字")
if email == "":
self.redirect("/post/%d" % int(pid), error=u"请填入邮箱地址")
if origin_content == "":
self.redirect("/post/%d" % int(pid), error=u"请输入评论内容")
number = db.query(Reply).filter(Reply.pid == pid).count() + 1
db.add(
Reply(pid=int(pid),
name=name,
email=email,
website=website,
content=content,
origin_content=origin_content,
number=number))
db.commit()
self.set_replyer(name, email, website)
self.redirect("/post/%d#%d" % (int(pid), int(number)))
async def __get_infos(list_id):
list_json = await api_call('list/{}'.format(list_id))
for link in list_json['links']:
if link['type'] == 'letterboxd':
url = link['url']
break
description = 'By **' + list_json['owner']['displayName'] + '**\n'
description += str(list_json['filmCount']) + ' films\nPublished '
description += list_json['whenPublished'].split('T')[0].strip() + '\n'
if list_json.get('descriptionLbml'):
description += format_text(list_json['descriptionLbml'], 300)
if list_json['previewEntries']:
poster_json = list_json['previewEntries'][0]['film'].get('poster')
if not poster_json:
return description, url, None, list_json['name']
for poster in poster_json['sizes']:
if poster['height'] > 400:
poster_url = poster['url']
break
return description, url, poster_url, list_json['name']
def post(self, pid, id):
self.check_admin()
name = self.get_argument("reply[name]", default='')
email = self.get_argument("reply[email]", default='')
website = self.get_argument("reply[website]", default='')
origin_content = self.get_argument("reply[content]", default='')
content = md(format_text(origin_content))
if name == "":
self.redirect("/post/%d" % int(pid), error=u"请填入名字")
if email == "":
self.redirect("/post/%d" % int(pid), error=u"请填入邮箱地址")
if origin_content == "":
self.redirect("/post/%d" % int(pid), error=u"请输入评论内容")
reply = db.query(Reply).get(id)
if reply is None:
raise tornado.web.HTTPError(404)
reply.name = name
reply.email = email
reply.website = website
reply.origin_content = origin_content
reply.content = content
db.commit()
self.set_replyer(name, email, website)
self.redirect("/post/%d#%d" % (int(pid), int(reply.number)))
def post(self, pid, id):
self.check_admin()
name = self.get_argument("reply[name]", default='')
email = self.get_argument("reply[email]", default='')
website = self.get_argument("reply[website]", default='')
origin_content = self.get_argument("reply[content]", default='')
content = md(format_text(origin_content))
if name == "":
self.redirect("/post/%d" % int(pid), error=u"请填入名字")
if email == "":
self.redirect("/post/%d" % int(pid), error=u"请填入邮箱地址")
if origin_content == "":
self.redirect("/post/%d" % int(pid), error=u"请输入评论内容")
reply = db.query(Reply).get(id)
if reply is None:
raise tornado.web.HTTPError(404)
reply.name = name
reply.email = email
reply.website = website
reply.origin_content = origin_content
reply.content = content
db.commit()
self.set_replyer(name, email, website)
self.redirect("/post/%d#%d" % (int(pid), int(reply.number)))