def absorb(repository, topic):
# overarching repository creation
os.mkdir(repository)
move_files(topic, repository)
mcdir(repository)
file_list = generic_file_extraction(topic.files)
for subtopic in topic.titles:
for file in file_list:
f_text = open(file, 'r+').read()
mcdir(f"{file.replace('.txt', '')}")
recorder = nlp(f_text)
# record entities
mcdir('Entities')
cwd = os.getcwd()
ent_list = list(recorder.ents)
# inside the Entities repository
for entity in ent_list:
# creating entity sub repositories based on label
mcdir(f'{entity.label_}')
mcdir(f'{entity}.txt')
# recording the entity in the sub repository
f = open(f'{entity}.txt', 'w+')
f.write(f'Entity Plain Text: {entity.text}\n')
f.write(f'Label: {entity.label_}\n')
pattern = re.compile('\W')
# sub('[^A-Za-z/ ]', '', n)
wp = search(re.sub(pattern, 'None', entity))
if wp is not None:
f.write(f'{wp.title} : {wp.url}\n')
f.write(f'{wikipedia.summary(wp.title, sentences=10)}')
os.chdir(cwd)
chback(2)
# record vocabulary
mcdir('Vocabulary')
for word in recorder:
if not word.is_stop and not os.path.exists(
f'{word}.txt'): # duplicate entities
doc = open(f'{word}.txt', 'w+')
doc.write(f'{word}\n')
# prints pos + explanation, fine grain pos + explanation
doc.write(f'Part of Speech:{word.pos_:{6}} '
f'{spacy.explain(word.pos_):{6}} '
f'{spacy.explain(word.tag_)}\n')
doc.write(f'Stem: {VDE.stemmer.stem(word)}')
# record the stem of the word
search(word)
# look up the definition of a word in the search engine, etc
chback(1)
chback(1)
os.rename(f'{file}', f"{file.replace('.txt', '')}/{file}")
os.chdir(repository)
def load_wiki(self, page):
if not self.valid_wiki(page.url):
return
pwiki = '//div[@class="mw-parser-output"]/*'
xwiki = engine.Path(pwiki, link=False)
results = engine.search(page, [xwiki])
if len(results) == 0:
return
rwiki = results[0]
wiki = ""
for child in rwiki:
if self.header.match(child.tag):
wiki += "\n"
wiki += "-" * 80
wiki += "\n"
wiki += etree.tostring(child, method="text", encoding="UTF-8")
wiki += "-" * 80
wiki += "\n"
if child.tag.decode("ascii", "ignore") == "p":
wiki += etree.tostring(child, method="text", encoding="UTF-8")
self.wiki = wiki
def worker(api, friends):
timestamp_start = str(datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'))
log_start = str((threading.currentThread().getName(), 'Launched'))
start = log_start + ':' + timestamp_start
print start
for friend in friends:
engine.index(INDEX, 'user', friend.id, social.userToJSON(friend))
request={"size":1,"sort":[{"id":{"order":"desc"}}], "query": {"match": {
"user.screen_name":friend.screen_name}}}
docs = engine.search(INDEX, 'tweet', request)
if (len(docs["hits"]["hits"]) > 0):
since_id = str(docs["hits"]["hits"][0][u'_id'])
else:
since_id = None
tweets = social.GetTweets(api, friend.screen_name, since_id)
for tweet in tweets:
engine.index(INDEX, 'tweet', tweet.id, social.tweetToJSON(tweet))
timestamp_end = str(datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'))
log_end = str((threading.currentThread().getName(), 'Finishing'))
end = log_end + ':' + timestamp_end
print end
return
def load_answers(self, page):
if not self.valid_url(page.url):
return
paccepted = '//div[@class="answer accepted-answer"]'
panswers = '//div[@class="answer"]'
panswer = '/table/tr/td[@class="answercell"]/div[@class="post-text"]'
xaccepted = engine.Path(paccepted + panswer, link=False)
xanswers = engine.Path(panswers + panswer, link=False)
results = engine.search(page, [xaccepted, xanswers])
self.results = None
raccepted = results[0]
ranswers = results[1]
answers = []
accepted = None
if len(raccepted) > 0:
accepted = etree.tostring(raccepted[0],
method="text",
encoding="UTF-8")
for answer in ranswers:
answers.append(
etree.tostring(answer, method="text", encoding="UTF-8"))
self.results = Answers("unimplemented", accepted, answers)
def search(self):
results = engine.search(self.searchbox.text())
self.clear()
for p in results:
self.listWidget.addItem(p)
for a in engine.posts[p]:
self.listWidget.addItem(a)
def result():
if request.method == 'POST':
address = request.form['q']
res = search(address)
results = filter_results(res)
return render_template("results.html", results=results)
return render_template('index.html')
def search(self):
'''Searches the database for relevant pages, then updates the results box
to show any matching results
'''
# Clear the previous search results
self.results_box.clear()
# search index for documents/urls relevant to searh_query
global FILE_URL_MAP
search_query = self.search_box.text()
results, num_results = engine.search(search_query)
url_list = []
if len(results[0]) == 0:
return
WEBPAGES_RAW_NAME = "WEBPAGES_RAW"
JSON_FILE_NAME = os.path.join(".", WEBPAGES_RAW_NAME, "bookkeeping.json")
FILE_URL_MAP = json.load(open(JSON_FILE_NAME), encoding="utf-8")
cleaner = Cleaner()
for filename in results:
with open(os.path.join(".", WEBPAGES_RAW_NAME, filename),"rb") as fp:
html_string = fp.read()
cleaned_document = lxml.html.document_fromstring(cleaner.clean_html(html_string))
#print((FILE_URL_MAP[filename],cleaned_document.text_content()))
url_list.append((FILE_URL_MAP[filename],cleaned_document.text_content()))
for i in url_list:
print(i[0])
#results = 5 * [(search_query, f"www.{search_query}.com", "example cont\nent")]
self.show_results(search_query, url_list, num_results)
def index():
query = request.args.get("q")
if query:
ctx = engine.search(query)
if ctx['redirect']:
return redirect(ctx['redirect'])
return render_template("results.html", **ctx)
return render_template("index.html")
def load_results(self, page):
xsection = engine.Path('//div[@class="section"]',link=False)
results = engine.search(page, xsection)
if len(results) != 1:
return
self.instruction = etree.tostring(results[0],method="text",encoding="UTF-8")
def runtime_game_handler(nickname, player_class, world):
# Create a new player and get his UID.
player_uid = world.add_player(nickname)
print "Welcome to this wonderful game!"
# Store the UID
CLIENTS.append((player_uid, 'Local Player'))
# Join the player's selected class
sel_class = "JOIN;"+player_class
world.set_player_attr(player_uid, 1, 'character', sel_class)
#!TODO: Sheit buus, protams, jaizmaina no raw_input uz pogu!
playing = True
while playing:
message = raw_input('command: > ').upper()
m_split = message.split(';')
if m_split[0] == 'JOIN':
# Join the game with the according character class
world.set_player_attr(player_uid, 1, 'character', message)
elif m_split[0] == 'PRINT':
'''Server always sends back the players visibility
area depending on player's class.
'''
gamefield_arr = world.gamefield_scope(player_uid)
print gamefield_arr
elif m_split[0] == 'PRINTALL':
# Print out the whole gamefield. For debugging purposes.
print ''
print ''
world.print_array() # For server side debugging
elif message == 'U':
data = 'UP'
world.set_player_attr(player_uid, 1, 'nextmove', data)
elif message == 'D':
data = 'DOWN'
world.set_player_attr(player_uid, 1, 'nextmove', data)
elif message == 'L':
data = 'LEFT'
world.set_player_attr(player_uid, 1, 'nextmove', data)
elif message == 'R':
data = 'RIGHT'
world.set_player_attr(player_uid, 1, 'nextmove', data)
elif m_split[0] == 'SCORE':
player = engine.search(world.players, 'uid', player_uid) # The player's dictionary
score = player['score']
print score
elif m_split[0] == 'PLIST':
msg = str(world.players)
print msg
elif message == 'QUIT':
# Remove the player from the world
world.del_player(player_uid)
# Remove the client from the list.
for client in CLIENTS:
if client[0] == player_uid:
CLIENTS.remove(client)
print "Client disconnected at: %s" % (':'.join(map(str, client))), time.asctime()
playing = False
def load_results(self, page):
xtitle = engine.Path('//h3[@class="r"]/a/text()',link=False)
xlink = engine.Path('//h3[@class="r"]/a/@href')
results = engine.search(page, [xtitle,xlink])
self.titles = []
self.links = []
for t,l in zip(results[0], results[1]):
self.titles.append(t)
self.links.append(l)
def search_time_limit(self, amount_of_time=5):
position = engine.start_state()
for _ in range(20):
position.push(list(position.legal_moves)[0])
self.logger.info("Searching for %d seconds", amount_of_time)
timestamp = time.time()
_, _ = engine.search(position, seconds=amount_of_time)
timestamp = time.time() - timestamp
difference = timestamp - amount_of_time
self.logger.info("Search took %d seconds", timestamp)
self.logger.info("Difference is %d seconds", difference)
self.assertGreaterEqual(.1, difference) # allow .1s of passed time
def load_search(self, page):
if not self.valid_search(page.url):
return
presult = '//div[@class="mw-search-result-heading"]/a'
xresult = engine.Path(presult, link=False)
results = engine.search(page, xresult)
for result in results:
print "UNIMPLEMENTED, ADD SUBTREE TO ENGINE"
print result.attrib['href'], result.attrib['title']
def load_questions(self, page):
if not self.valid_search(page.url):
return
psummary = '//div[@class="summary"]/div[@class="result-link"]'
xsummary = engine.Path(psummary, link=False)
plink = "./span/a/@href"
ptitle = "./span/a/text()"
ptext = "./span"
xtitle = engine.Path(ptitle, link=False)
xlink = engine.Path(plink, link=True)
results = engine.search(page, xsummary)
if len(results) == 0:
writeln("[-] no results found")
return
if not isinstance(self.results, Questions):
self.results = Questions("ERR", [])
for summary in results:
page = engine.Page(page.url, tree=summary)
link = engine.search(page, xlink)
title = engine.search(page, xtitle)
if len(link) == 0 or len(title) == 0:
continue
link = link[0].strip()
title = title[0].strip()[3:]
self.results.questions.append(Question(title, link))
def do_next(self, args):
if not self.page:
writeln("[-] no results loaded!")
return
xpath = engine.Path('//a[@id="pnnext"]/@href')
n = engine.search(self.page, xpath)
if not n:
writeln("[-] no more results!")
return
self.page = engine.Page(n[0], load=True)
self.lpr(self.page)
def home():
query = request.args.get('query')
fields = request.args.getlist('fields')
genres = request.args.getlist('genres')
page = request.args.get('page')
if not page:
page = 1
if not query:
return render_template('index.html')
else:
results = engine.search(query, fields, genres, int(page))
return render_template('results.html', results=results)
def post(self):
args = parser.parse_args()
link = args['link']
search_terms = args['search_terms']
analysis_interval = args['analysis_interval']
start_time = args['start_time']
end_time = args['end_time']
results = {}
# results = search(link, search_terms, analysis_interval, start_time, end_time)
try:
results = search(link, search_terms, analysis_interval, start_time,
end_time)
except Exception as e:
return {'message': str(e)}, 422
return results
def worker(api, friends):
timestamp_start = str(
datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'))
log_start = str((threading.currentThread().getName(), 'Launched'))
start = log_start + ':' + timestamp_start
print start
for friend in friends:
engine.index(INDEX, 'user', friend.id, social.userToJSON(friend))
request = {
"size": 1,
"sort": [{
"id": {
"order": "desc"
}
}],
"query": {
"match": {
"user.screen_name": friend.screen_name
}
}
}
docs = engine.search(INDEX, 'tweet', request)
if (len(docs["hits"]["hits"]) > 0):
since_id = str(docs["hits"]["hits"][0][u'_id'])
else:
since_id = None
tweets = social.GetTweets(api, friend.screen_name, since_id)
for tweet in tweets:
engine.index(INDEX, 'tweet', tweet.id, social.tweetToJSON(tweet))
timestamp_end = str(
datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'))
log_end = str((threading.currentThread().getName(), 'Finishing'))
end = log_end + ':' + timestamp_end
print end
return
def Runner(build_index, parse_query, search, determine_relevance):
logging.log(GRADING, "")
logging.log(GRADING, "-- STARTING TO RUN --")
index = {}
documentlist = ["us_constitution", "magna_carta", "un_charter"]
build_index(index, documentlist)
logging.log(GRADING, "INDEX")
logging.log(GRADING, index)
print "There are {0} documents in the index".format(len(documentlist))
print "There are {0} terms in the index".format(len(index))
logging.log(GRADING, "STATISTICS")
logging.log(GRADING, "{0} docs, {1} terms".format(
len(documentlist),
len(index),
))
user_query = raw_input("enter your query>")
query = parse_query(user_query)
logging.log(GRADING, "QUERY")
logging.log(GRADING, query)
candidate_set = search(query, index)
logging.log(GRADING, "CANDIDATE_SET")
logging.log(GRADING, candidate_set)
relevant_results = determine_relevance(query, candidate_set)
logging.log(GRADING, "RELEVANT_RESULTS")
logging.log(GRADING, relevant_results)
results = relevant_results.items()
results.sort(key=lambda i: i[1], reverse=True)
print 'The best results for "{0}" are:'.format(user_query)
for result in results:
print result
print '[end of results]'
logging.log(GRADING, "-- ENDED RUN CLEANLY --")
def Main():
form = FormContent()
query_option = form["query_option"][0] # Determine which option is desired
city = "None" # Code for
city_name = "None"
if form.has_key("city"):
city = form["city"][0]
city_name = functs.convert_station(city)
year = "None"
if form.has_key("year"):
year = form["year"][0]
month = "None"
str_month = "None"
if form.has_key("month"):
month = form["month"][0]
str_month = functs.convert_month("0"+month)
day = "None"
if form.has_key("day"):
day = form["day"][0]
if year == "none" or year == "None":
style.SendError("You need to specify a search date.")
style.header("Historical Iowa Weather Data Search Engine","white") # Standard Setup HTML Document
style.std_top("Query Results in Iowa Weather Data") # Standard Header Information
print '<TABLE NOBORDER>'
print '<TR><TH colspan="4">Search Paramenters:</TH><TH colspan="6"><font color="red">Time Constraints:</red></TH></TR>'
print '<TR><TH bgcolor="#EEEEE">Query Option:</TH><TD>'+query_option+'</TD>'
print '<TH bgcolor="#EEEEE">Station Option:</TH><TD>'+city_name+'</TD>'
print '<TH bgcolor="#EEEEE"><font color="red">Year:</font></TH><TD>'+year+'</TD>'
print '<TH bgcolor="#EEEEE"><font color="red">Month:</font></TH><TD>'+str_month+'</TD>'
print '<TH bgcolor="#EEEEE"><font color="red">Day:</font></TH><TD>'+day+'</TD>'
print '</TR></TABLE>'
if city == "None":
print '<H2 align="center"><font color="blue"><U>Please Enter a city!!</U></font></H2>'
style.std_bot()
sys.exit()
results = engine.search(query_option, city, year, month, day)
print '<HR>'
junk_string = 'query_option='+query_option+'&city='+city+'&year='+year+'&month='+month+'&day='+day
print '<a href="download.py?'+junk_string+'"><B>Click to download this data set</B></a>'
print '<HR>'
if len(results) == 0:
print '<P>This Query did not find any results in the Database system.<BR>'
print '<P>Please review your query above and try again.<BR>'
else:
print '<H2 align="center"><font color="blue"><U>Weather Data for '+city_name+', Iowa</U></font></H2>'
table_header()
for i in range(len(results)):
city = results[i][0]
day = results[i][1]
climoweek = results[i][2]
high = results[i][3]
low = results[i][4]
rain = results[i][5]
snow = results[i][6]
result_row(city, day, str(high), str(low), str(rain), str(snow) )
table_footer()
style.std_bot()
def search(self):
key_iter = []
search_kword_num = 0
search_url_num = 0
for key in self.keys_list:
# 输出HTML文件
search_kword_num = search_kword_num + 1
if os.path.isdir(self.work_path + '/result'):
pass
else:
os.mkdir(self.work_path + '/result')
if self.breakpoint:
filename = self.work_path + \
'/result/%s-%s.html' % ((sys.argv[1]
).decode('utf8'), key.decode('utf8'))
else:
filename = self.work_path + \
'/result/%s.html' % (key.decode('utf8'))
# 写文件
with codecs.open(filename, 'wb', "utf-8") as f:
f.write(unicode(
'<html><head><meta http-equiv="content-type" content="text/html;charset=utf-8"></head><body>'))
self.br.set_cookiejar(cookielib.LWPCookieJar())
for engine in self.engine_list:
engine_name = engine.engine.__class__.__name__
if self.breakpoint and self.num_runinfo.has_option(engine_name, key):
ri = RunInfo(
key, num=int(self.num_runinfo.get(engine_name, key)))
else:
ri = RunInfo(key)
key_iter.append([engine_name, engine.search(key), ri])
while key_iter != []:
for k_iter in key_iter:
self.exist_list = []
try:
k_iter[2].page += 1
# next函数相当重要
result_list = next(k_iter[1])
except StopIteration:
# print 'remove ',k_iter[0]
key_iter.remove(k_iter)
for k_iter in key_iter:
print " ", k_iter[0]
continue
except Exception, e:
# print k_iter[0],'error'
# print e
self.error_list.append([e, k_iter[0], k_iter[2]])
key_iter.remove(k_iter)
continue
if result_list:
# print "============================"
# print "key:",key,'engine:',k_iter[0]
# print "***************************"
f.write(
('<p>============================</p>\n<p>key:%s engine:%s</p>\n<p>****************************</p>\n' % (key, k_iter[0])).decode('utf8'))
for result in result_list:
k_iter[2].num += 1
result['engine'] = k_iter[0]
result['num'] = k_iter[2].num
result['key'] = key
result['time_now'] = time.strftime(
'%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
# print
# result['num'],result['title']#,result['url']
self.exist_list.append(result['url'])
f.write(unicode('<p>%s %s <a href="%s" target="_blank">%s</a></p>\n' % (
result['time_now'], result['num'], result['url'], result['title'])))
self.num_runinfo.set(k_iter[0], key, k_iter[2].num)
# 什么是nif，什么是rif
with open(self.numinfo_file, 'wb') as nif:
self.num_runinfo.write(nif)
with open(self.linkinfo_file, 'wb') as rif:
self.link_runinfo.write(rif)
# print "============================"
f.write('<p>============================</p>\n')
# 更新URL长度
search_url_num = search_url_num + \
len(self.exist_list)
'''
存储mongo数据库
'''
# print '///////////////////////'
# print self.exist_list
# print '//////////////////////////'
try:
self.mongo_operate.add_gray_list(
self.exist_list, self.objectID)
except Exception, e:
sys.stderr.write(
'%s\n' % MongoError(e, 'meta_run add gray'))
sys.stderr.write(
' task_id: %s\n' % self.task_id)
# print
# '---------------------seccess###################################'
self.update_running_state(
search_url_num, search_kword_num)
f.write('</body></html>')
start = 'Start: ' + timestamp_start
print(start)
if (len(sys.argv)==2):
api_param = sys.argv[1]
else:
raise Exception('Error en cantidad de parametros ingresados!!!')
api = social.api(api_param)
for account in accounts:
print('Indexing ' + account)
user = social.GetUser(api,account)
id = user.id
engine.index(INDEX, 'user', id, social.userToJSON(user))
request={"size":1,"sort":[{"id":{"order":"desc"}}], "query": {"match": {
"user.screen_name":account}}}
docs = engine.search(INDEX, 'tweet', request)
if (len(docs["hits"]["hits"]) > 0):
since_id = str(docs["hits"]["hits"][0][u'_id'])
else:
since_id = None
tweets = social.GetTweets(api, account, since_id)
for tweet in tweets:
print('Tweet> ' + tweet.text)
engine.index(INDEX, 'tweet', tweet.id, social.tweetToJSON(tweet))
def test_search_at_mate(self):
position = mated_position()
move_suggestion, resulting_position = engine.search(position, 2)
self.assertEqual(position.fen(), resulting_position.fen())
self.assertIsNone(move_suggestion)
def search(self):
key_iter = []
search_kword_num = 0
search_url_num = 0
for key in self.keys_list:
# 输出HTML文件
search_kword_num = search_kword_num + 1
if os.path.isdir(self.work_path + '/result'):
pass
else:
os.mkdir(self.work_path + '/result')
if self.breakpoint:
filename = self.work_path + \
'/result/%s-%s.html' % ((sys.argv[1]
).decode('utf8'), key.decode('utf8'))
else:
filename = self.work_path + \
'/result/%s.html' % (key.decode('utf8'))
# 写文件
with codecs.open(filename, 'wb', "utf-8") as f:
f.write(
unicode(
'<html><head><meta http-equiv="content-type" content="text/html;charset=utf-8"></head><body>'
))
self.br.set_cookiejar(cookielib.LWPCookieJar())
for engine in self.engine_list:
engine_name = engine.engine.__class__.__name__
if self.breakpoint and self.num_runinfo.has_option(
engine_name, key):
ri = RunInfo(
key,
num=int(self.num_runinfo.get(engine_name, key)))
else:
ri = RunInfo(key)
key_iter.append([engine_name, engine.search(key), ri])
while key_iter != []:
for k_iter in key_iter:
self.exist_list = []
try:
k_iter[2].page += 1
# next函数相当重要
result_list = next(k_iter[1])
except StopIteration:
# print 'remove ',k_iter[0]
key_iter.remove(k_iter)
for k_iter in key_iter:
print " ", k_iter[0]
continue
except Exception, e:
# print k_iter[0],'error'
# print e
self.error_list.append([e, k_iter[0], k_iter[2]])
key_iter.remove(k_iter)
continue
if result_list:
# print "============================"
# print "key:",key,'engine:',k_iter[0]
# print "***************************"
f.write((
'<p>============================</p>\n<p>key:%s engine:%s</p>\n<p>****************************</p>\n'
% (key, k_iter[0])).decode('utf8'))
for result in result_list:
k_iter[2].num += 1
result['engine'] = k_iter[0]
result['num'] = k_iter[2].num
result['key'] = key
result['time_now'] = time.strftime(
'%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
# print
# result['num'],result['title']#,result['url']
self.exist_list.append(result['url'])
f.write(
unicode(
'<p>%s %s <a href="%s" target="_blank">%s</a></p>\n'
% (result['time_now'], result['num'],
result['url'], result['title'])))
self.num_runinfo.set(k_iter[0], key, k_iter[2].num)
# 什么是nif，什么是rif
with open(self.numinfo_file, 'wb') as nif:
self.num_runinfo.write(nif)
with open(self.linkinfo_file, 'wb') as rif:
self.link_runinfo.write(rif)
# print "============================"
f.write('<p>============================</p>\n')
# 更新URL长度
search_url_num = search_url_num + \
len(self.exist_list)
'''
存储mongo数据库
'''
# print '///////////////////////'
# print self.exist_list
# print '//////////////////////////'
try:
self.mongo_operate.add_gray_list(
self.exist_list, self.objectID)
except Exception, e:
sys.stderr.write(
'%s\n' %
MongoError(e, 'meta_run add gray'))
sys.stderr.write(' task_id: %s\n' %
self.task_id)
# print
# '---------------------seccess###################################'
self.update_running_state(search_url_num,
search_kword_num)
f.write('</body></html>')
start = 'Start: ' + timestamp_start
print start
if (len(sys.argv)==2):
api_param = sys.argv[1]
else:
raise Exception('Error en cantidad de parametros ingresados!!!')
api = social.api(api_param)
for account in accounts:
print 'Indexing ' + account
user = social.GetUser(api,account)
id = user.__getattribute__('_id')
engine.index(INDEX, 'user', id, social.userToJSON(user))
request={"size":1,"sort":[{"id":{"order":"desc"}}], "query": {"match": {
"user.screen_name":account}}}
docs = engine.search(INDEX, 'tweet', request)
if (len(docs["hits"]["hits"]) > 0):
since_id = str(docs["hits"]["hits"][0][u'_id'])
else:
since_id = None
tweets = social.GetTweets(api, account, since_id)
for tweet in tweets:
print 'Tweet> ' + tweet.text
engine.index(INDEX, 'tweet', tweet.id, social.tweetToJSON(tweet))
def search_command():
list1.delete(0,END)
for row in engine.search(title_text.get(), author_text.get(), year_text.get(), isbn_text.get()):
list1.insert(END,row)
def Main():
style.header("Download Dataset from IowaWx Archive", "white")
print "<H2>Instructions for downloading from the PALS server</H2>"
query_option = functs.get_content("query_option")
city = functs.get_content("city")
year = functs.get_content("year")
month = functs.get_content("month")
day = functs.get_content("day")
if month == "None":
str_month = "None"
else:
str_month = functs.convert_month("0" + month)
if city == "None":
str_city = "None"
else:
str_city = functs.convert_station(city)
print "<HR><H3>1. Review Search Parameters....</H3>"
print "<TABLE NOBORDER>"
print '<TR><TH colspan="4">Search Paramenters:</TH><TH colspan="6"><font color="red">Time Constraints:</red></TH></TR>'
print '<TR><TH bgcolor="#EEEEE">Query Option:</TH><TD>' + query_option + "</TD>"
print '<TH bgcolor="#EEEEE">Station Option:</TH><TD>' + str_city + "</TD>"
print '<TH bgcolor="#EEEEE"><font color="red">Year:</font></TH><TD>' + year + "</TD>"
print '<TH bgcolor="#EEEEE"><font color="red">Month:</font></TH><TD>' + str_month + "</TD>"
print '<TH bgcolor="#EEEEE"><font color="red">Day:</font></TH><TD>' + day + "</TD>"
print "</TR></TABLE>"
print "<HR>"
print "<H3>2. Instructions for downloading this data.</H3>"
print "Below a link with appear and you need to hold the shift key down and click on the link.<BR>"
print "This should allow you to save the text file locally, so then you can do what ever you want with it.<BR>"
print "<HR>"
url = "/archivewx/iowawx/tmp/" + filename + ".txt"
print "<H3>3. Creating data file... (May take a few seconds.)</H3>"
results = engine.search(query_option, city, year, month, day)
for i in range(len(results)):
city = results[i][0]
year = results[i][1]
month = results[i][2]
day = results[i][3]
climoweek = results[i][4]
high = results[i][5]
low = results[i][6]
rain = results[i][7]
snow = results[i][8]
file.write(city + "\t" + year + "\t" + month + "\t" + day + "\t" + climoweek + "\t" + high + "\t")
file.write(low + "\t" + rain + "\t" + snow + "\n")
file.close()
print "<BR>File created successfully!! <BR><HR>"
print "<H3>4. Download file</H3>"
print '<a href="' + url + '">Shift-Click Here, to download file</a><BR>'
style.std_bot()
def search_page(self):
return [str(x[0][0]) for x in engine.search(self.page,self.path)]
