def html_daily_stats():
html = "<b>Daily count (" + str(len(logview.get_log(None, None, None, None, None))) + " total)</b>\n"
date1 = datetime.date(2012, 8, 6) # the beginning of time
date2 = datetime.date.today()
day_count = (date2 - date1).days + 1
for d in [d for d in (date1 + datetime.timedelta(n) for n in range(day_count)) if d <= date2]:
log = logview.get_log(None, str(d), None, None, None)
html += "<br/>" + str(d) + " : " + str(len(log)) + "\n"
html += "<p/>"
return html
def get_logger_gps(): log = logview.get_log(None, None, None, None, None) gps = [] for row in log: (date, lat, lng) = row[2:5] if lat is not None and lng is not None: gps.append([date,lat,lng]) return gps
def index(self, keyword = None, date1 = None, date2 = None, location = None, limit = None): # get log according to parameters given if keyword is None and date1 is None and location is None: date1 = str(datetime.date.today()) if len(logview.get_log(None, date1, None, None, limit))==0: date1 = str(datetime.date.today() - datetime.timedelta(1)) log = logview.get_log(keyword, date1, date2, location, limit) media = logview.get_media(date1, date2) html = '<div id="left">' html += logview.html_log(log) html += '</div>' html += '<div id="right">' html += mapbox.html_get_map(log) html += logview.html_media(media) html += logview.html_calendar() html += '</div>' html = make_page(html, ['mapbox', 'lightbox'], ['mapbox', 'jquery-1.7.2.min', 'lightbox'], True) return html
def get_all_text():
logs = logview.get_log(None, None, None, None, None)
alltext = ""
all_people = []
all_tags = []
all_locations = []
for log in logs:
# clean up text
alltext += log[5] + " "
log_lower = log[5].lower()
logp = re.compile("~([A-Za-z0-9]+)").findall(log[5])
logt = re.compile("#([A-Za-z0-9]+)").findall(log_lower)
logl = re.compile("@([A-Za-z0-9]+)").findall(log_lower)
post_people = []
post_tags = []
post_locations = []
for p in logp:
post_people.append(p)
all_people.append(p)
for t in logt:
post_tags.append(t)
all_tags.append(t)
for l in logl:
post_locations.append(l)
all_locations.append(l)
all_tokens = Counter(nltk.word_tokenize(alltext))
all_people = Counter(all_people)
all_tags = Counter(all_tags)
all_locations = Counter(all_locations)
totalwords = 0
for t in all_tokens:
totalwords += all_tokens[t]
# TOKENS
html = "<br/>Total tokens: " + str(totalwords) + "\n"
html += "<br/>Unique tokens: " + str(len(all_tokens)) + "\n"
html += '<table border=0 width="90%"><tr>\n'
html += "<td>\n"
# TOP PEOPLE
# needs fix: should not count double mentions in single line
html += "<p/>Unique people: " + str(len(all_people)) + "\n"
html += "<ul>\n"
for p in all_people.most_common(NUM_TOP_PEOPLE):
html += '<br/><li><a href="/?keyword=' + p[0] + '">' + p[0] + " (" + str(p[1]) + ")</li>\n"
html += "</ul>\n"
html += "</td><td>\n"
# TOP TAGS
html += "<p/>Unique tags: " + str(len(all_tags)) + "\n"
html += "<ul>\n"
for p in all_tags.most_common(NUM_TOP_TAGS):
html += '<br/><li><a href="/?keyword=' + p[0] + '">' + p[0] + " (" + str(p[1]) + ")</li>\n"
html += "</ul>\n"
html += "</td><td>\n"
# TOP LOCATIONS
html += "<p/>Unique locations: " + str(len(all_locations)) + "\n"
html += "<ul>\n"
for p in all_locations.most_common(NUM_TOP_LOCATIONS):
html += '<br/><li><a href="/?keyword=' + p[0] + '">' + p[0] + " (" + str(p[1]) + ")</li>\n"
html += "</ul>\n"
html += "</td></tr></table>\n"
return html
