File size: 5,464 Bytes
ee3e666 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
import streamlit as st
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.service import Service as ChromeService
from webdriver_manager.core.os_manager import ChromeType
import time
import sys
import re
import transformers
import pandas as pd
import torch
from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
import io
import plotly.express as px
import zipfile
from streamlit_extras.stylable_container import stylable_container
# sidebar
with st.sidebar:
with stylable_container(
key="test_button",
css_styles="""
button {
background-color: yellow;
border: 1px solid black;
padding: 5px;
color: black;
}
""",
):
st.button("DEMO APP")
expander = st.expander("**Important notes on the Google Maps Reviews Sentiment Analysis App**")
expander.write('''
**How to Use**
This app works with the URL of the Google Maps Reviews. Paste the URL and press the 'Sentiment Analysis' button to perform sentiment analysis on your Google Maps Reviews.
**Usage Limits**
You can perform sentiment analysis on Google Maps Reviews up to 5 times.
**Subscription Management**
This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own Google Maps Reviews Sentiment Analysis Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app in five business days. If you wish to delete your Account with us, please contact us at [email protected]
**Customization**
To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
**File Handling and Errors**
For any errors or inquiries, please contact us at [email protected]
''')
tokenizer = DistilBertTokenizer.from_pretrained("tabularisai/robust-sentiment-analysis")
model = DistilBertForSequenceClassification.from_pretrained("tabularisai/robust-sentiment-analysis")
def scroll_and_check_for_new_reviews(driver, current_review_count):
"""Scrolls down the page and checks if new reviews have loaded."""
try:
last_review = driver.find_elements(By.CSS_SELECTOR, 'div.jftiEf')[-1]
driver.execute_script("arguments[0].scrollIntoView(true);", last_review)
time.sleep(3) # Increased sleep time to allow for loading
new_review_count = len(driver.find_elements(By.CSS_SELECTOR, 'div.jftiEf'))
return new_review_count > current_review_count
except Exception as e:
st.error(f"Error during scrolling: {e}")
return False
def scrape_google_reviews(url):
"""Scrapes Google reviews from the given URL and performs sentiment analysis."""
try:
options = Options()
options.add_argument("--headless")
options.add_argument("--disable-gpu")
options.add_argument("--no-sandbox")
options.add_argument("--disable-dev-shm-usage")
options.add_argument("--start-maximized")
service = Service(ChromeDriverManager(chrome_type=ChromeType.CHROMIUM).install())
driver = webdriver.Chrome(service=service, options=options)
driver.get(url)
current_review_count = 0
while scroll_and_check_for_new_reviews(driver, current_review_count):
current_review_count = len(driver.find_elements(By.CSS_SELECTOR, 'div.jftiEf'))
st.write(f"Total reviews loaded: {current_review_count}")
reviews = driver.find_elements(By.CSS_SELECTOR, 'div.jftiEf')
review_data = []
for review_elem in reviews:
try:
reviewer_name = review_elem.find_element(By.CSS_SELECTOR, '.d4r55').text.strip()
except Exception:
reviewer_name = 'No name'
try:
review_text = review_elem.find_element(By.CSS_SELECTOR, '.wiI7pd').text.strip()
except Exception:
review_text = 'No review text'
rating = 0
try:
reviews_element = review_elem.find_element(By.CSS_SELECTOR, "span[role='img']")
reviews_text = reviews_element.get_attribute("aria-label")
match = re.search(r'(\d+(?:\.\d+)?) stars', reviews_text)
if match:
rating = float(match.group(1))
except Exception:
pass
try:
date_elem = review_elem.find_element(By.CSS_SELECTOR, '.rsqaWe')
review_date = date_elem.text.strip()
except Exception:
review_date = 'No date'
review_data.append({
'reviewer_name': reviewer_name,
'review_text': review_text,
'rating': rating,
'review_date': review_date,
})
driver.quit()
df = pd.DataFrame(review_data)
df[df["review_text"].str.contains("No review text")==False]
st.dataframe(df)
|