def topic_ana(request):
topics_str = _get(request, 'topic')
if not topics_str:
return HttpResponseRedirect('/')
topics = topics_str.split(common.TOPIC_SEPARATOR)
topic_dicts = [dict(topic=t, rm_q='') for t in topics]
if len(topics) > 1:
for topic_dict in topic_dicts:
tmp_topics = topics[:]
tmp_topics.remove(topic_dict['topic'])
topic_dict['rm_q'] = _join_topic_str(tmp_topics,
common.TOPIC_SEPARATOR)
related_topics = db.get_related_topics(topics)
all_amount = db.get_articles_amount_by_topics(topics)
for item in related_topics:
item['q'] = topics_str + common.TOPIC_SEPARATOR + item['title']
item['percentage'] = 100* item['amount'] / all_amount
if item['percentage'] ==0:
item['percentage'] = 1
start = _shift_datetime(_truncate_day(datetime.datetime.now()), days=-7)
all_7d_amount = db.get_articles_amount_by_topics(topics, start=start)
related_7d_topics = db.get_related_topics(topics, start=start)
for item in related_7d_topics:
item['q'] = topics_str + common.TOPIC_SEPARATOR + item['title']
item['percentage'] = 100* item['amount'] / all_7d_amount
if item['percentage'] ==0:
item['percentage'] = 1
return render_to_response('topic_analytics.html',
dict(topics=topic_dicts,
topic=topics_str,
all_7d_amount=all_7d_amount,
related_7d_topics=related_7d_topics,
all_amount=all_amount,
related_topics=related_topics))
def dtopic(request):
t = _get(request, 't')
if not t:
return HttpResponseRedirect('/')
filename = os.path.join(DATA_ROOT, 'topic', t)
#if not os.path.exists(filename) or True:
if True:
with open(filename, 'wb') as f:
writer = UnicodeWriter(f)
topics = t.split(common.TOPIC_SEPARATOR)
related_topics = db.get_related_topics(topics, limit=10)
writer.writerow(['topic', 'articles'])
writer.writerows([[d['title'], str(d['amount'])] for d in related_topics])
wrapper = FileWrapper(file(filename))
response = HttpResponse(wrapper, content_type='text/plain')
response['Content-Length'] = os.path.getsize(filename)
return response
def topic(request):
topics_str = _get(request, 'topic')
if not topics_str:
return HttpResponseRedirect('/')
limit = _get(request, 'limit')
if limit is None:
limit = 100
elif limit == 'all':
limit = 0
else:
try:
limit = int(limit)
except Exception:
limit = 100
topics = topics_str.split(common.TOPIC_SEPARATOR)
topic_dicts = [dict(topic=t, rm_q='') for t in topics]
if len(topics) == 1:
articles = db.list_articles_by_topic(topics[0], limit=limit)
else:
articles = db.list_articles_by_topics(topics, limit=limit)
for topic_dict in topic_dicts:
tmp_topics = topics[:]
tmp_topics.remove(topic_dict['topic'])
topic_dict['rm_q'] = _join_topic_str(tmp_topics,
common.TOPIC_SEPARATOR)
def _process_row(a):
a['created_date'] = a['created'][:10] #.timepstr('%Y-%M-%D')
a['url'] = urllib.unquote(a['url'])
a['source_url'] = urllib.unquote(a['source_url'])
return a
articles = [_process_row(a) for a in articles]
limit = limit if len(articles) == limit else 0
related_topics = db.get_related_topics(topics, limit=10)
for item in related_topics:
item['q'] = topics_str + common.TOPIC_SEPARATOR + item['title']
highlight_pattern=_join_topic_str(topics, common.DISPLAY_SEPARATOR)
return render_to_response('topic.html',
dict(topics=topic_dicts,
topic=topics_str,
highlight_pattern=highlight_pattern,
articles=articles,
limit=limit,
related_topics=related_topics))
