Upload 2 files
Browse files- app.py +56 -0
- requirements.txt +60 -0
app.py
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import requests
|
3 |
+
from bs4 import BeautifulSoup
|
4 |
+
import re
|
5 |
+
|
6 |
+
# Function to scrape only visible text from the given URL
|
7 |
+
def scrape_visible_text_from_url(url):
|
8 |
+
try:
|
9 |
+
response = requests.get(url)
|
10 |
+
response.raise_for_status()
|
11 |
+
soup = BeautifulSoup(response.content, 'html.parser')
|
12 |
+
|
13 |
+
# Remove script, style, and other non-visible tags
|
14 |
+
for tag in soup(["script", "style", "meta", "link", "noscript", "header", "footer", "aside", "nav", "img"]):
|
15 |
+
tag.extract()
|
16 |
+
|
17 |
+
# Get the header content
|
18 |
+
header_content = soup.find("header")
|
19 |
+
header_text = header_content.get_text() if header_content else ""
|
20 |
+
|
21 |
+
# Get the paragraph content
|
22 |
+
paragraph_content = soup.find_all("p")
|
23 |
+
paragraph_text = " ".join([p.get_text() for p in paragraph_content])
|
24 |
+
|
25 |
+
# Combine header and paragraph text
|
26 |
+
visible_text = f"{header_text}\n\n{paragraph_text}"
|
27 |
+
|
28 |
+
# Remove multiple whitespaces and newlines
|
29 |
+
visible_text = re.sub(r'\s+', ' ', visible_text)
|
30 |
+
return visible_text.strip()
|
31 |
+
except Exception as e:
|
32 |
+
st.error(f"Error occurred while scraping the data: {e}")
|
33 |
+
return None
|
34 |
+
|
35 |
+
# Streamlit UI
|
36 |
+
def main():
|
37 |
+
st.title("Web Data Scraper")
|
38 |
+
|
39 |
+
# Get the URL from the user
|
40 |
+
url_input = st.text_input("Enter the URL of the web page:", "")
|
41 |
+
|
42 |
+
if st.button("Scrape Visible Text"):
|
43 |
+
if url_input:
|
44 |
+
# Extract visible text from the URL
|
45 |
+
data = scrape_visible_text_from_url(url_input)
|
46 |
+
if data:
|
47 |
+
st.success("Visible text successfully scraped!")
|
48 |
+
st.subheader("Scraped Text:")
|
49 |
+
st.write(data)
|
50 |
+
else:
|
51 |
+
st.warning("Failed to scrape visible text from the URL.")
|
52 |
+
else:
|
53 |
+
st.warning("Please enter a valid URL.")
|
54 |
+
|
55 |
+
if __name__ == "__main__":
|
56 |
+
main()
|
requirements.txt
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
aiohttp==3.8.5
|
2 |
+
aiosignal==1.3.1
|
3 |
+
altair==5.0.1
|
4 |
+
async-timeout==4.0.2
|
5 |
+
attrs==23.1.0
|
6 |
+
beautifulsoup4==4.12.2
|
7 |
+
blinker==1.6.2
|
8 |
+
bs4==0.0.1
|
9 |
+
cachetools==5.3.1
|
10 |
+
certifi==2023.7.22
|
11 |
+
charset-normalizer==3.2.0
|
12 |
+
click==8.1.6
|
13 |
+
decorator==5.1.1
|
14 |
+
frozenlist==1.4.0
|
15 |
+
gitdb==4.0.10
|
16 |
+
GitPython==3.1.32
|
17 |
+
idna==3.4
|
18 |
+
importlib-metadata==6.8.0
|
19 |
+
Jinja2==3.1.2
|
20 |
+
jsonschema==4.18.4
|
21 |
+
jsonschema-specifications==2023.7.1
|
22 |
+
markdown-it-py==3.0.0
|
23 |
+
MarkupSafe==2.1.3
|
24 |
+
mdurl==0.1.2
|
25 |
+
multidict==6.0.4
|
26 |
+
numpy==1.25.2
|
27 |
+
openai==0.27.8
|
28 |
+
packaging==23.1
|
29 |
+
pandas==2.0.3
|
30 |
+
Pillow==9.5.0
|
31 |
+
protobuf==4.23.4
|
32 |
+
pyarrow==12.0.1
|
33 |
+
pydeck==0.8.0
|
34 |
+
Pygments==2.15.1
|
35 |
+
Pympler==1.0.1
|
36 |
+
python-dateutil==2.8.2
|
37 |
+
python-dotenv==1.0.0
|
38 |
+
pytz==2023.3
|
39 |
+
pytz-deprecation-shim==0.1.0.post0
|
40 |
+
referencing==0.30.0
|
41 |
+
requests==2.31.0
|
42 |
+
rich==13.5.2
|
43 |
+
rpds-py==0.9.2
|
44 |
+
six==1.16.0
|
45 |
+
smmap==5.0.0
|
46 |
+
soupsieve==2.4.1
|
47 |
+
streamlit==1.25.0
|
48 |
+
tenacity==8.2.2
|
49 |
+
toml==0.10.2
|
50 |
+
toolz==0.12.0
|
51 |
+
tornado==6.3.2
|
52 |
+
tqdm==4.65.0
|
53 |
+
typing_extensions==4.7.1
|
54 |
+
tzdata==2023.3
|
55 |
+
tzlocal==4.3.1
|
56 |
+
urllib3==2.0.4
|
57 |
+
validators==0.20.0
|
58 |
+
watchdog==3.0.0
|
59 |
+
yarl==1.9.2
|
60 |
+
zipp==3.16.2
|