JssuniScrap

JssuniScrap

# Initialize Data Frame
df = pd.DataFrame()

# Names
df['Name'] = [result.find('h2').text for result in results]

# Designation
df['Designation'] = [result.find('p').contents[1].strip(' ') for result in results]

# Email
df['Email'] = [result.find('p').contents[4].strip(' ') for result in results]

# Qualifications
df['Qualifications'] = [result.find('p').contents[7].strip(' ') for result in results]

# Create function to get number of publications written
def get_no_publications(result):
    try:
        publications = int(result.find('p').contents[10].strip(' '))
    except:
        publications = 0
    
    return publications

# Number of Publications
df['NumberOfPublications'] = [get_no_publications(result) for result in results]

# Export to csv without indices
df.to_csv('JssunPharmaceuticsDepartmentInfo.csv', index=False)