Update app.py
Browse files
app.py
CHANGED
|
@@ -7,10 +7,20 @@ import heapq
|
|
| 7 |
|
| 8 |
# NLTK downloads
|
| 9 |
nltk.download('punkt')
|
|
|
|
| 10 |
nltk.download('stopwords')
|
| 11 |
|
| 12 |
# Function to summarize text
|
| 13 |
def summarize_text(url):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
scraped_data = urllib.request.urlopen(url)
|
| 15 |
article = scraped_data.read()
|
| 16 |
parsed_article = bs.BeautifulSoup(article,'lxml')
|
|
|
|
| 7 |
|
| 8 |
# NLTK downloads
|
| 9 |
nltk.download('punkt')
|
| 10 |
+
|
| 11 |
nltk.download('stopwords')
|
| 12 |
|
| 13 |
# Function to summarize text
|
| 14 |
def summarize_text(url):
|
| 15 |
+
|
| 16 |
+
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'}
|
| 17 |
+
request = urllib.request.Request(url, headers=headers)
|
| 18 |
+
scraped_data = urllib.request.urlopen(request)
|
| 19 |
+
|
| 20 |
+
article = scraped_data.read()
|
| 21 |
+
|
| 22 |
+
# ... Rest of your existing code ...
|
| 23 |
+
|
| 24 |
scraped_data = urllib.request.urlopen(url)
|
| 25 |
article = scraped_data.read()
|
| 26 |
parsed_article = bs.BeautifulSoup(article,'lxml')
|