def count_with_negation(fin_dict, transcript):
"""
Count positive and negative words with negation check. Account for simple negation only for positive words.
negation is occurring within three words preceding a positive words.
"""
pos_count = 0
neg_count = 0
pos_words = []
neg_words = []
input_words = re.findall(r'\b([a-zA-Z]+n\'t|[a-zA-Z]+\'s|[a-zA-Z]+)\b', transcript.lower())
word_count = len(input_words)
for i in range(0, word_count):
if input_words[i] in fin_dict['Negative']:
neg_count += 1
neg_words.append(input_words[i])
if input_words[i] in fin_dict['Positive']:
if i >= 3:
if negated(input_words[i - 1]) or negated(input_words[i - 2]) or negated(input_words[i - 3]):
neg_count += 1
neg_words.append(input_words[i] + ' (with negation)')
else:
pos_count += 1
pos_words.append(input_words[i])
elif i == 2:
if negated(input_words[i - 1]) or negated(input_words[i - 2]):
neg_count += 1
neg_words.append(input_words[i] + ' (with negation)')
else:
pos_count += 1
pos_words.append(input_words[i])
elif i == 1:
if negated(input_words[i - 1]):
neg_count += 1
neg_words.append(input_words[i] + ' (with negation)')
else:
pos_count += 1
pos_words.append(input_words[i])
elif i == 0:
pos_count += 1
pos_words.append(input_words[i])
results = [word_count, pos_count, neg_count, pos_words, neg_words]
return results
def no(strg):
# return int(''.join(filter(str.isdigit, strg)))
return re.findall(r"[-+]?\d*\.\d+|\d+", strg)[0]
#### loop for finding the site and email of each resort
loop_counter=1
for resort in resorts:
# looking for the website
## frist googling for this website
search_page =fetch_results(resort +' website',10,'en')
search_page =BeautifulSoup(search_page,'lxml')
sites_in_results =search_page.findAll('div',{'class':'r'})
sites_in_results =[tag.a['href'] for tag in sites_in_results]
resort_site =desired_link(sites_in_results,resort)
# looking for email
## frist googling for email
search_page =fetch_results(resort+' email',10,'en')
emails_in_results =re.findall(email_pattern,search_page)
if len(emails_in_results)==0 :
print()
driver.get(resort_site)
sleep(1)
search_page=driver.page_source
emails_in_results=search_page.findall(email_pattern)
if(len(emails_in_results)==0):
search_page=BeautifulSoup(search_page,'lxml')
contact_us=search_page.findAll('a')
contact_us=[tag['href'] for tag in contact_us]
contact_us=desired_link(contact_us,'contact us')
driver.get(contact_us)
emails_in_results=search_page.findall(email_pattern)
if(len(emails_in_results)==0):
from bs4 import BeautifulSoup
import urllib.request
from bs4 import re
page = urllib.request.urlopen('http://services.housing.berkeley.edu/FoodPro/dining/static/todaysentrees.asp')
soup = BeautifulSoup(page)
print(soup)
items = soup.find_all('font')
print('BREAK')
for item in items:
print(item)
food = re.findall(r'>[\w\s]*<',str(items)) #Looks for items between brackets
food_list = []
for item in food:
item = item[1:len(item)-1]
print(item)
food_list.append(item)
food_list = food_list[12:]
print(food_list)