Spaces:
Sleeping
Sleeping
Commit
·
37ee6a5
1
Parent(s):
1ec143e
Add support for more content classes
Browse files- beautiful_soup/app.py +15 -0
beautiful_soup/app.py
CHANGED
@@ -61,6 +61,21 @@ def get_main_content( soup ):
|
|
61 |
if content is not None:
|
62 |
print('Has .region--content class.')
|
63 |
return content
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
return None
|
66 |
|
|
|
61 |
if content is not None:
|
62 |
print('Has .region--content class.')
|
63 |
return content
|
64 |
+
|
65 |
+
content = soup.find( "div", { "class": "article" } )
|
66 |
+
if content is not None:
|
67 |
+
print('Has .article class.')
|
68 |
+
return content
|
69 |
+
|
70 |
+
content = soup.find( "div", { "class": "article-inner_html" } )
|
71 |
+
if content is not None:
|
72 |
+
print('Has .article-inner_html class.')
|
73 |
+
return content
|
74 |
+
|
75 |
+
content = soup.find( "article" )
|
76 |
+
if content is not None:
|
77 |
+
print('Has article tag.')
|
78 |
+
return content
|
79 |
|
80 |
return None
|
81 |
|