def consume(item):
package = {}
root = etree.fromstring(item, parser=etree.XMLParser(recover=True))
log.debug("Processing " + str(root))
# Initial process
package['class'] = root.tag
package['pubkey'] = root.get('key')
package['authors'] = []
for child in root:
if child.tag == 'author':
package['authors'] += [child.text]
else:
package[child.tag] = get_text_from_node(child)
package['authors'] = list(set(package['authors']))
# Post process
package['type'] = package['pubkey'].split('/')[0]
if 'year' in package and package['year'] is not None and package['year'].isdigit():
package['year'] = int(package['year'])
else:
package['year'] = 0
package['month'] = int(root.get('mdate').split('-')[1])
if 'pages' in package and package['pages'] is not None:
package['total_page'] = get_total_page(package['pages'])
else:
package['total_page'] = get_total_page('')
# if 'volume' in package:
# package['volume'] = int(package['volume'])
# if 'number' in package:
# package['number'] = int(package['number'])
# Collect
collector.collect(package)
def scan(self):
collect(self.building_comboBox.currentText(),
self.RP_comboBox.currentText(), 1)
label = QLabel("Scan is successfuly done", self.dialog)
label.setGeometry(120, 70, 250, 24)
label.move(100, 100)
label.setObjectName("label")
# btnDialog = QPushButton("위치별 수집내역 확인", self.dialog)
# btnDialog.setGeometry(1700, 1000, 250, 50)
# btnDialog.move(130, 150)
# btnDialog.clicked.connect(self.scan_check)
btnDialog2 = QPushButton("Send data to server", self.dialog)
btnDialog2.setGeometry(50, 50, 250, 50)
btnDialog2.move(50, 250)
btnDialog2.clicked.connect(self.dialog_close)
btnDialog2 = QPushButton("Don't send data", self.dialog)
btnDialog2.setGeometry(50, 50, 250, 50)
btnDialog2.move(300, 250)
btnDialog2.clicked.connect(self.dialog_close)
self.dialog.setWindowTitle('scan complete')
self.dialog.setWindowModality(Qt.ApplicationModal)
self.dialog.resize(600, 400)
self.dialog.show()
def test_collect(self):
virt_platform = collector.collect(_CONFIG_PATH)
self.assertTrue("hosts" in virt_platform)
self.assertEqual(len(virt_platform["hosts"]), 4)
for host in ['node1', 'node2', 'node3']:
self.assertTrue("disks" in virt_platform["hosts"][host])
self.assertEqual(virt_platform["hosts"][host]["nics"][0]['mac'],
'dddd')
def run(self):
item = self.queue.get()
while item != None:
try:
url = item['url']
key = item['key']
constraint = item['constraint']
data = fetch(url)
if data == None:
self.logger.info('Not fetched: %s because type != text/html', url)
else:
links = get_all_links(data, base = url)
feeds = get_all_feeds(data, base = url)
interesting = collect(links)
if interesting:
self.collection_mutex.acquire()
if key not in self.collection:
self.collection[key] = {'feeds':{}}
if feeds:
for feed in feeds:
self.collection[key]['feeds'][feed['href']] = feed['type']
for service, accounts in interesting.items():
if service not in self.collection[key]:
self.collection[key][service] = {}
for a,u in accounts.items():
self.collection[key][service][a] = {'url': u, 'depth':constraint.depth}
self.collection_mutex.release()
for l in links:
new_constraint = constraint.inherit(url, l)
if new_constraint == None:
continue
self.mutex.acquire()
if l not in self.visited_urls:
self.queue.put({'url':l, 'key':key, 'constraint': new_constraint})
self.visited_urls.add(l)
self.mutex.release()
except HTTPError:
self.logger.info('HTTPError exception on url: %s', url)
self.queue.task_done()
item = self.queue.get()
self.queue.task_done() # task_done on None
def login():
if request.method == 'POST':
if request.form.get('submitBtn') == 'submitBtn':
username = request.form.get('accountOptions')
userinfo = get_userinfo(username)
status = collect(userinfo['userid'], userinfo['token'])
return redirect(url_for('user', username=username))
elif request.form.get('removeBtn') == 'removeBtn':
username = request.form.get('accountOptions')
delete_user(username)
usernames = get_usernames()
return render_template('login.html',
input_error=False,
usernames=usernames)
def __collect_links(start_url, route_table, visit_limit):
''' Test how link collecting works in small sandbox
@types: str, dict[str, tuple[int, str, str]], int -> dict[str, UrlInfo]
@param route_table:
routing table defines small subset of WEB
that will be used for crawler testing
each record in table is composed of:
- URL to visit
- status code and mime type for HEAD request
- list of outgoing links included in visited page
'''
def get_from_route(url):
print "GET from route: ", url
record = route_table.get(url)
code, content = 404, None
if record:
code, _, content = record
response = mock.Mock()
response.text = content
response.status_code = code
return response
def head_from_route(url):
r = route_table.get(url, (404, None, None))
status_code, mimetype, _ = r
response = mock.Mock()
response.status_code = status_code
response.headers.get.return_value = mimetype
return response
with contextlib.nested(
mock.patch("requests.get", get_from_route),
mock.patch("requests.head", head_from_route),
mock.patch("grequests.get", get_from_route),
mock.patch("grequests.head", head_from_route),
mock.patch("grequests.map", list)):
return collector.collect(start_url, visit_limit)
if __name__ == "__main__":
falgs, flags = sys.argv[1], sys.argv[2:]
progress_bar_size = 10
start = time.time()
n = 2
if "-m" in flags: # model
ftrained = flags[flags.index("-m") + 1]
else:
ftrained = "trained.txt"
if "-c" in flags: # collect
fcollection = flags[flags.index("-t") + 1]
collect(4800, fcollection)
if "-t" in flags: # train
fcollection = flags[flags.index("-t") + 1]
out("Processing " + fcollection + " - ")
c = Analyzer.fromcollection(n, fcollection)
c.save(ftrained)
out("saved to " + ftrained + ".\n")
# collect list of raw algorithms
out("Processing " + falgs + " - extracted ")
alg_re = re.compile(
"([URFLDBMESurfldbxyz][2']?[2']? )+([URFLDBMESurfldbxyz][2']?[2']?)"
) # CE algs
raw = []
prevlen = str(len(raw))
def do_collect():
print("Data updating...")
return collect()
def collect_game(href):
print(f'Collecting https://www.basketball-reference.com{href}')
html = collect('https://www.basketball-reference.com' + href)
if html is None:
return []
game_data = {}
team_data = []
player_data = []
game_data['id'] = href.split('/')[2].split('.')[0]
game_scoreboard = html.select('div.scorebox > div')[2]
game_data['date'] = game_scoreboard.contents[1].contents[0]
if len(game_scoreboard.contents[2].contents) >= 1:
game_data['venue'] = game_scoreboard.contents[2].contents[0].split(
',')[0]
else:
game_data['venue'] = ''
is_home = 0
for team_html in html.select('div.scorebox > div')[:2]:
data = {}
team_data.append(data)
team_link = team_html.select('strong a')[0]
data['id'] = team_link['href'].split('/')[2]
data['name'] = team_link.contents[0]
data['points'] = int(team_html.select('div.score')[0].contents[0])
score_parts = list(
map(lambda x: int(x),
team_html.contents[4].contents[0].split('-')))
data['season_wins'] = score_parts[0]
data['season_losses'] = score_parts[1]
data['is_home'] = is_home
is_home = 1
if team_data[0]['points'] > team_data[1]['points']:
team_data[0]['season_wins'] -= 1
team_data[1]['season_losses'] -= 1
else:
team_data[1]['season_wins'] -= 1
team_data[0]['season_losses'] -= 1
for team in team_data:
starting = 1
for stat_row in html.select(f'#box-' + team['id'] +
'-game-basic tbody tr'):
data = {}
if stat_row.has_attr('class'):
starting = 0
elif len(stat_row.select('td')) > 1:
player_data.append(data)
player_link = stat_row.select('th a')[0]
data['id'] = player_link['href'].split('/')[3].split('.')[0]
data['name'] = player_link.contents[0]
data['starting'] = starting
for stat_cell in stat_row.select('td'):
stat = stat_cell['data-stat']
if not stat.endswith('pct') and stat != 'plus_minus':
data[stat_cell['data-stat']] = stat_cell.contents[0]
for curr_team in team_data:
prefix = 'team_'
if curr_team['id'] != team['id']:
prefix = 'opp_team_'
for key in curr_team:
data[prefix + key] = str(curr_team[key])
for key in game_data:
data[f'game_{key}'] = str(game_data[key])
return player_data
for curr_team in team_data:
prefix = 'team_'
if curr_team['id'] != team['id']:
prefix = 'opp_team_'
for key in curr_team:
data[prefix + key] = str(curr_team[key])
for key in game_data:
data[f'game_{key}'] = str(game_data[key])
return player_data
year = start_year
while year <= end_year:
for month in months:
html = collect(
f'https://www.basketball-reference.com/leagues/NBA_{year}_games-{month}.html'
)
if html is not None:
for row in html.select('#schedule tr'):
th = row.select('th')[0]
if th.has_attr('csk'):
links = row.select('a')
if len(links) >= 4:
href = row.select('a')[3]['href']
player_data.extend(collect_game(href))
keys = player_data[0].keys()
with open(f'../data/nba_{year}.csv', 'w', encoding='utf-8',
newline='') as file:
dict_writer = csv.DictWriter(file, keys)
dict_writer.writeheader()
def collect(symbol):
"""Get a stock from AV."""
return collector.collect(symbol)
