-
-
Save nveenverma/38898fcfce6c21c1518367d18dc97152 to your computer and use it in GitHub Desktop.
This file contains 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 get_top_questions(url, question_count): | |
# WARNING: Only enter one of these 3 values [15, 30, 50]. | |
# Since, stackoverflow, doesn't display any other size questions list | |
url = url + "?sort=votes&pagesize={}".format(question_count) | |
# Using requests module for downloading webpage content | |
response = requests.get(url) | |
# Parsing html data using BeautifulSoup | |
soup = bs(response.content, 'html.parser') | |
body = soup.find('body') | |
# Extracting Top Questions | |
question_links = body1.select("h3 a.question-hyperlink") | |
error_checking(question_links, question_count) # Error Checking | |
questions = [i.text for i in question_links] # questions list | |
# Extracting Summary | |
summary_divs = body1.select("div.excerpt") | |
error_checking(summary_divs, question_count) # Error Checking | |
summaries = [i.text.strip() for i in summary_divs] # summaries list | |
# Extracting Tags | |
tags_divs = body1.select("div.summary > div:nth-of-type(2)") | |
error_checking(tags_divs, question_count) # Error Checking | |
a_tags_list = [i.select('a') for i in tags_divs] # tag links | |
tags = [] | |
for a_group in a_tags_list: | |
tags.append([a.text for a in a_group]) # tags list | |
# Extracting Number of votes | |
vote_spans = body1.select("span.vote-count-post strong") | |
error_checking(vote_spans, question_count) # Error Checking | |
no_of_votes = [int(i.text) for i in vote_spans] # votes list | |
# Extracting Number of answers | |
answer_divs = body1.select("div.status strong") | |
error_checking(answer_divs, question_count) # Error Checking | |
no_of_answers = [int(i.text) for i in answer_divs] # answers list | |
# Extracting Number of views | |
div_views = body1.select("div.supernova") | |
error_checking(div_views, question_count) # Error Checking | |
no_of_views = [i['title'] for i in div_views] | |
no_of_views = [i[:-6].replace(',', '') for i in no_of_views] | |
no_of_views = [int(i) for i in no_of_views] # views list | |
# Putting all of them together | |
df = pd.DataFrame({'question': questions, | |
'summary': summaries, | |
'tags': tags, | |
'no_of_votes': no_of_votes, | |
'no_of_answers': no_of_answers, | |
'no_of_views': no_of_views}) | |
return df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment