status = 1
elif botanical_found:
status = 1
else:
print(chalk.red.bold("plant "), common_name, botanical_name,
chalk.red.bold(" not found in data"))
common_not_found = 1
botanical_not_found = 1
both_found = 0
botanical_found = 0
common_found = 0
status = 0
with open('mbg-data.csv', 'a') as writeFile:
writer = csv.writer(writeFile)
print(common_not_found)
print(botanical_not_found)
if (common_not_found == 0 or botanical_not_found == 0):
writer.writerow([
'', common_name, botanical_name, status, common_found,
botanical_found, both_found, r.url,
'http://www.missouribotanicalgarden.org/' +
plant_seach_link, ''
])
else:
print(chalk.magenta("Plant was not found on MGB site"))
writer.writerow([
'', common_name, botanical_name, status, common_found,
botanical_found, both_found, r.url, 'not found', ''
])
# Requst the plantFinder for plant based on common name
botanical_name_req = {'basic': botanicalName}
# print(chalk.green(commonNameOriginal))
time.sleep(1)
r = requests.get('http://www.missouribotanicalgarden.org/PlantFinder/PlantFinderProfileResults.aspx', params=botanical_name_req)
# print(chalk.yellow.bold('common name search url'),r.url)
soup = BeautifulSoup(r.text,'html.parser')
span = soup.find(id="dnn_ctr4158_SearchResults_lblNoResults")
if span:
# print(chalk.red(span.text))
if span.text == "We're sorry, but no results were found matching your criteria. Please revise your search criteria.":
print(chalk.red.bold('plant not found with botanical name'),botanicalName)
botanical_not_found = 1
with open('MBGBotanicalNames-output.csv','a') as writeFile:
writer = csv.writer(writeFile)
print(chalk.magenta("writing to csv that plant was not found"))
writer.writerow(
['Not found',
'0', # Common Name Original
'0', # Common Name - MGB
botanicalName,
'0', # Botanical Name - MGB
'0', # type
'0', # family
'0', # native range
'0', # zone
'0', # zone low
'0', # zone high
'0', # height
'0', # height low
'0', # heigh high
if (price < lowPrice):
print(chalk.green.bold('Sending text to ' + buyingOrSelling))
client.messages.create(
to=myNumber,
from_=twilioNumber,
body="Price dropped below ${:.2f}! Time to {} some shares of {}!".
format(lowPrice, buyingOrSelling, tickerSymbol))
break
# Wait for price increase
elif (price > highPrice):
print(chalk.green.bold('Sending text to ' + buyingOrSelling))
client.messages.create(
to=myNumber,
from_=twilioNumber,
body="Price increased above ${:.2f}! Time to {} your shares of {}!"
.format(highPrice, buyingOrSelling, tickerSymbol))
break
else:
# price = chalk.green("$" + price)
print(
chalk.magenta('Current price: ') +
chalk.green.bold('$' + str(price)) +
chalk.magenta(' Continuing to monitor ') +
chalk.magenta.bold(tickerSymbol) + chalk.magenta(' prices...'))
time.sleep(30)
price = getPrice(price)
# Shut down driver
driver.quit()
def findHeightWordInSentences(lemmatizedSentences, plantName, category,
wikiLink):
foundHeight = False
with open('plantHeightData.csv', 'a', newline='') as csvfile:
writer = csv.writer(csvfile)
for sentence in lemmatizedSentences:
for word in sentence:
if (word == 'height' or word == 'tall'):
print(chalk.green.bold('height found for'), plantName)
foundHeight = True
sentenceThatContainHeightKeyword = " ".join(
str(x) for x in sentence)
# print(sentenceThatContainHeightKeyword,'\n')
# filterdSentence = tokenizer.tokenize(sentenceThatContainHeightKeyword)
# sentenceThatContainHeightKeyword = " ".join(str(x) for x in filterdSentence)
# print("plant Name is :" ,plantName, sentenceThatContainHeightKeyword);
doc = nlp(sentenceThatContainHeightKeyword)
count = 0
plant_height_data = []
for token in doc:
t = token.text
if t == 'm' or t == 'meter' or t == 'metre' or t == 'ft' or t == 'foot' or t == 'cm' or t == 'centimetre' or t == 'in':
# if len(doc) > (token.i+1):
# next_token = doc[token.i + 1]
prev_token = doc[token.i - 1]
if prev_token.like_num:
count += 1
# print("token",token," token.i",token.i," len(doc)",len(doc))
token_sentence = doc[prev_token.i:token.i + 1]
print("case#1",
chalk.yellow.bold(token_sentence))
plant_height_data.append(token_sentence)
if doc[prev_token.i -
2].like_num: # 1 to 2 unit
count += 1
token_sentence = doc[prev_token.i -
2:token.i + 1]
print("case#2",
chalk.blue.bold(token_sentence))
plant_height_data.append(token_sentence)
else:
pass
else: #get data for case#3 x-x unit
if prev_token.is_punct == False:
token_sentence = doc[prev_token.i:token.i +
1]
print("case#3",
chalk.magenta(
token_sentence)) #x-x uni
plant_height_data.append(token_sentence)
else:
pass # do nothing if theres a punct mark
# if next_token.lower_ == "m" or next_token.lower_ == 'ft' or next_token.lower_ == 'meter' or next_token.lower_ == 'metre' or next_token.lower_ == 'cm' or next_token.lower_ == 'in' or next_token.lower_ == 'foot':
# count += 1
# token_sentence = doc[prev_token.i:next_token.i + 1]
# print('Height sentence',token_sentence)
# unit = token_sentence[len(token_sentence) - 1:len(token_sentence)]
# print(unit)
# writer.writerow([plantName,category,unit,'',token_sentence,'',wikiLink,sentenceThatContainHeightKeyword,''])
# unit cleanup
plant_height_data_str = []
plant_height_data_str_ft = ''
plant_height_data_str_cm = ''
plant_height_data_str_m = ''
plant_height_data_str_in = ''
for valueWithUnit in plant_height_data:
stringData = valueWithUnit.text
stringData = stringData.replace("-", " ")
stringData = stringData.replace("centimetre", "cm")
stringData = stringData.replace("foot", "ft")
stringData = stringData.replace("meter", "m")
stringData = stringData.replace("inch", "in")
stringData = stringData.replace('–', ' ')
stringData = stringData.replace('to', ' ')
stringData = stringData.replace(',', '')
stringData = stringData.replace('1/2', '0.5')
if stringData.find('in') > 0:
plant_height_data_str_in = plant_height_data_str_in + stringData
plant_height_data_str_in = plant_height_data_str_in.replace(
'in', '')
if stringData.find('ft') > 0:
plant_height_data_str_ft = plant_height_data_str_ft + stringData
plant_height_data_str_ft = plant_height_data_str_ft.replace(
'ft', '')
if stringData.find(' m') > 0:
plant_height_data_str_m = plant_height_data_str_m + stringData
plant_height_data_str_m = plant_height_data_str_m.replace(
'm', '')
if stringData.find(' cm') > 0:
plant_height_data_str_cm = plant_height_data_str_cm + stringData
plant_height_data_str_cm = plant_height_data_str_cm.replace(
'cm', '')
plant_height_data_str.append(stringData)
print(chalk.red(plantName), plant_height_data)
print(chalk.green(plantName), plant_height_data_str)
# inch
# remove all characters
plant_height_data_str_in = removeAlphabets(
plant_height_data_str_in)
print(chalk.yellow(plantName), 'inch values',
plant_height_data_str_in)
plant_height_data_str_in = plant_height_data_str_in.split()
try:
plant_height_data_str_in = list(
map(float, plant_height_data_str_in))
plant_height_data_str_in = sorted(
plant_height_data_str_in)
print(chalk.cyan.bold(plantName), 'inch values',
plant_height_data_str_in)
except ValueError:
pass
# ft
plant_height_data_str_ft = removeAlphabets(
plant_height_data_str_ft)
print(chalk.yellow(plantName), 'ft values',
plant_height_data_str_ft)
plant_height_data_str_ft = plant_height_data_str_ft.split()
try:
plant_height_data_str_ft = list(
map(float, plant_height_data_str_ft))
plant_height_data_str_ft = sorted(
plant_height_data_str_ft)
print(chalk.cyan.bold(plantName), 'ft values',
plant_height_data_str_ft)
except ValueError:
pass
# m
plant_height_data_str_m = removeAlphabets(
plant_height_data_str_m)
print(chalk.yellow(plantName), 'm values',
plant_height_data_str_m)
plant_height_data_str_m = plant_height_data_str_m.split()
try:
plant_height_data_str_m = list(
map(float, plant_height_data_str_m))
plant_height_data_str_m = sorted(
plant_height_data_str_m)
print(chalk.cyan.bold(plantName), 'm values',
plant_height_data_str_m)
except ValueError:
pass
# cm
plant_height_data_str_cm = removeAlphabets(
plant_height_data_str_cm)
print(chalk.yellow(plantName), 'cm values',
plant_height_data_str_cm)
plant_height_data_str_cm = plant_height_data_str_cm.split()
try:
plant_height_data_str_cm = list(
map(float, plant_height_data_str_cm))
plant_height_data_str_cm = sorted(
plant_height_data_str_cm)
print(chalk.cyan.bold(plantName), 'cm values',
plant_height_data_str_cm)
except ValueError:
pass
if (len(plant_height_data_str_in) > 0):
temp = ['x'] * 10
for index, value in enumerate(
plant_height_data_str_in):
temp[index] = value
writer.writerow([
plantName, category, 'in', temp[0], temp[1],
temp[2], temp[3], temp[4], temp[5], temp[6],
temp[7], temp[8], temp[9], wikiLink,
sentenceThatContainHeightKeyword
])
if (len(plant_height_data_str_cm) > 0):
temp = ['x'] * 10
for index, value in enumerate(
plant_height_data_str_cm):
temp[index] = value
writer.writerow([
plantName, category, 'cm', temp[0], temp[1],
temp[2], temp[3], temp[4], temp[5], temp[6],
temp[7], temp[8], temp[9], wikiLink,
sentenceThatContainHeightKeyword
])
if (len(plant_height_data_str_ft) > 0):
temp = ['x'] * 10
for index, value in enumerate(
plant_height_data_str_ft):
temp[index] = value
writer.writerow([
plantName, category, 'ft', temp[0], temp[1],
temp[2], temp[3], temp[4], temp[5], temp[6],
temp[7], temp[8], temp[9], wikiLink,
sentenceThatContainHeightKeyword
])
if (len(plant_height_data_str_m) > 0):
temp = ['x'] * 10
for index, value in enumerate(plant_height_data_str_m):
temp[index] = value
writer.writerow([
plantName, category, 'm', temp[0], temp[1],
temp[2], temp[3], temp[4], temp[5], temp[6],
temp[7], temp[8], temp[9], wikiLink,
sentenceThatContainHeightKeyword
])
# if (count > 0):
# print(count,chalk.red.bold('tokens found in'),plantName,'\n')
# else:
# writer.writerow([plantName,category,'not found','','not found','',wikiLink,sentenceThatContainHeightKeyword,''])
# print(count,chalk.red('tokens matched in'),plantName,'\n')
if (foundHeight == False):
print(chalk.red("No Height for "), plantName)
with open('plantHeightData.csv', 'a', newline='') as csvfile:
writer = csv.writer(csvfile)
writer.writerow([
plantName, category, 'x', 'x', 'x', 'x', 'x', 'x', 'x', 'x',
'x', 'x', 'x', wikiLink, 'x'
])