Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -4,7 +4,8 @@ import requests
|
|
| 4 |
import bs4
|
| 5 |
import lxml
|
| 6 |
|
| 7 |
-
def find_it1(url):
|
|
|
|
| 8 |
source = urllib.request.urlopen(url).read()
|
| 9 |
soup = bs4.BeautifulSoup(source,'lxml')
|
| 10 |
# title of the page
|
|
@@ -23,15 +24,21 @@ def find_it1(url):
|
|
| 23 |
print(soup.p)
|
| 24 |
print(soup.find_all('p'))
|
| 25 |
for paragraph in soup.find_all('p'):
|
|
|
|
| 26 |
print(paragraph.string)
|
| 27 |
print(str(paragraph.text))
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
| 29 |
for url in soup.find_all('a'):
|
| 30 |
print(url.get('href'))
|
|
|
|
| 31 |
print(soup.get_text())
|
| 32 |
-
|
| 33 |
|
| 34 |
|
|
|
|
|
|
|
| 35 |
def find_it2(url):
|
| 36 |
response = requests.get(url,a1=None,q2=None,q3=None)
|
| 37 |
try:
|
|
|
|
| 4 |
import bs4
|
| 5 |
import lxml
|
| 6 |
|
| 7 |
+
def find_it1(url,q1=None,q2=None):
|
| 8 |
+
out = []
|
| 9 |
source = urllib.request.urlopen(url).read()
|
| 10 |
soup = bs4.BeautifulSoup(source,'lxml')
|
| 11 |
# title of the page
|
|
|
|
| 24 |
print(soup.p)
|
| 25 |
print(soup.find_all('p'))
|
| 26 |
for paragraph in soup.find_all('p'):
|
| 27 |
+
|
| 28 |
print(paragraph.string)
|
| 29 |
print(str(paragraph.text))
|
| 30 |
+
out.append(paragraph)
|
| 31 |
+
out.append(paragraph.string)
|
| 32 |
+
out.append(paragraph.text)
|
| 33 |
+
|
| 34 |
for url in soup.find_all('a'):
|
| 35 |
print(url.get('href'))
|
| 36 |
+
|
| 37 |
print(soup.get_text())
|
|
|
|
| 38 |
|
| 39 |
|
| 40 |
+
return out
|
| 41 |
+
|
| 42 |
def find_it2(url):
|
| 43 |
response = requests.get(url,a1=None,q2=None,q3=None)
|
| 44 |
try:
|