Created
May 24, 2021 23:00
-
-
Save thunderInfy/2da449e906e81fac1dbe5a0f6192ba16 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def construct_df(soup): | |
L = soup.findAll(True, {'class':['center-name-title','center-name-text', 'slots-box']}) | |
# obtaining class specific information from soup results | |
M = [] | |
for i in L: | |
class_names = i.get('class') | |
if class_names == ['center-name-title']: | |
ADD = i.get_text() | |
elif class_names == ['center-name-text']: | |
M.append((class_names, ADD + " " + i.get_text())) | |
else: | |
M.append((class_names, i.get_text())) | |
# constructing pandas dataframe | |
pushelement = None | |
data = [] | |
rownames = [] | |
for i in M: | |
if i[0] == ['center-name-text']: | |
rownames.append(i[1]) | |
if pushelement is not None: | |
data.append(pushelement) | |
pushelement = [] | |
else: | |
pushelement.append(i[1]) | |
if pushelement is not None: | |
data.append(pushelement) | |
# Create the pandas DataFrame | |
df = pd.DataFrame(data) | |
df.index = rownames | |
return df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment