Update app.py
Browse files
app.py
CHANGED
@@ -20,8 +20,14 @@ def find_all(url,q=None,num=None):
|
|
20 |
print(soup.p)
|
21 |
print(soup.find_all('p'))
|
22 |
for tag in soup.find_all():
|
23 |
-
|
24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
for url in soup.find_all('a'):
|
26 |
print(url.get('href'))
|
27 |
|
@@ -36,7 +42,7 @@ def find_it(url,q=None,num=None):
|
|
36 |
source = urllib.request.urlopen(url).read()
|
37 |
soup = bs4.BeautifulSoup(source,'lxml')
|
38 |
for p in soup.find_all(f'{q}'):
|
39 |
-
out.append(p)
|
40 |
out.append(p.string)
|
41 |
out.append(p.parent)
|
42 |
|
|
|
20 |
print(soup.p)
|
21 |
print(soup.find_all('p'))
|
22 |
for tag in soup.find_all():
|
23 |
+
try:
|
24 |
+
n = url.get(tag.string)
|
25 |
+
rawp.append(f'{tag.name}:{tag.string}[{n}]')
|
26 |
+
except Exception as e:
|
27 |
+
print (e)
|
28 |
+
rawp.append(f'{tag.name}:{tag.string}')
|
29 |
+
|
30 |
+
#rawp.append(tag.string)
|
31 |
for url in soup.find_all('a'):
|
32 |
print(url.get('href'))
|
33 |
|
|
|
42 |
source = urllib.request.urlopen(url).read()
|
43 |
soup = bs4.BeautifulSoup(source,'lxml')
|
44 |
for p in soup.find_all(f'{q}'):
|
45 |
+
#out.append(p)
|
46 |
out.append(p.string)
|
47 |
out.append(p.parent)
|
48 |
|