def get_related_data_to_question(ques_url): html = urlopen(QUESTIONS_BASE_URL + ques_url) soup = BeautifulSoup(html, "lxml") question_summary = soup.find("a", "question-hyperlink").text question_desc = soup.find("div", "post-text").text user_details = soup.find("div", "user-details") user = user_details.find('a').text profile_url = user_details.find('a')['href'] profile_url += BASE_URL rating = user_details.find('span').text tags = soup.find_all("a", "post-taglist") tags = tags[0].text.split(' ') category = "" answer = soup.find("div", "answer").text #user = soup.find("a", id="ct100_ct100_MC_AMC_QuestionAuthorRepInfo_MemberName") insert_data(question_id=question_desc, user=user, rating=rating, tags=tags, profile_url=profile_url, source_website=BASE_URL, answer=re.escape(answer), correct_answer=re.escape(answer), category=category)
def get_related_data_to_question(ques_url): html = urlopen(QUESTIONS_BASE_URL + ques_url) soup = BeautifulSoup(html, "lxml") question_summary = soup.find("a", "question-hyperlink").text question_desc = soup.find("div", "post-text").text user_details = soup.find("div", "user-details") user = user_details.find('a').text profile_url = user_details.find('a')['href'] profile_url = QUESTIONS_BASE_URL + profile_url rating = user_details.find('span').text tags = soup.find_all("div", "post-taglist") tags = str(tags[0].text.split(' ')) category = "" answer = soup.find("div", "answer").text import pdb pdb.set_trace() insert_data(question_id=question_desc, user=user, rating=rating, tags=tags, profile_url=profile_url, source_website=BASE_URL, answer=re.escape(answer), correct_answer=re.escape(answer), category=category)
def get_related_data_to_question(ques_url): html = urlopen(QUESTIONS_BASE_URL + ques_url) soup = BeautifulSoup(html, "lxml") question_desc = soup.find("div", "header").text user = soup.find("div", "member-rep-container").a.text profile_url = soup.find("div", "member-rep-container").a["href"] profile_url += BASE_URL rating = soup.find("div", "member-rep-container").span.text tags = get_all_tags(soup) category = "" answer = soup.find("div", "answer-row answer first").find("div", "text").text #user = soup.find("a", id="ct100_ct100_MC_AMC_QuestionAuthorRepInfo_MemberName") insert_data(question_short=question_desc, user=user, rating=rating, tags=tags, profile_url=profile_url, source_website=BASE_URL, answer=re.escape(answer), correct_answer=re.escape(answer), category=category)
def get_related_data_to_question(ques_url): html = urlopen(QUESTIONS_BASE_URL + ques_url) soup = BeautifulSoup(html, "lxml") question_summary = soup.find("a", "question-hyperlink").text question_desc = soup.find("div", "post-text").text user_details = soup.find("div", "user-details") user = user_details.find('a').text profile_url = user_details.find('a')['href'] profile_url = QUESTIONS_BASE_URL + profile_url rating = user_details.find('span').text tags = soup.find_all("div", "post-taglist") tags = str(tags[0].text.split(' ')) category = "" answer = soup.find("div", "answer").text insert_data(question_short=question_desc, user=user, rating=rating, tags=tags, profile_url=profile_url, source_website=BASE_URL, answer=re.escape(answer), correct_answer=re.escape(answer), category=category)
def get_related_data_to_question(ques_url): html = urlopen(QUESTIONS_BASE_URL + ques_url) soup = BeautifulSoup(html, "lxml") question_desc = soup.find("div", "header").text user = soup.find("div", "member-rep-container").a.text profile_url = soup.find("div", "member-rep-container").a["href"] profile_url += BASE_URL rating = soup.find("div", "member-rep-container").span.text tags = get_all_tags(soup) category = "" answer = soup.find("div", "answer-row answer first").find("div", "text").text #user = soup.find("a", id="ct100_ct100_MC_AMC_QuestionAuthorRepInfo_MemberName") insert_data(question_id=question_desc, user=user, rating=rating, tags=tags, profile_url=profile_url, source_website=BASE_URL, answer=re.escape(answer), correct_answer=re.escape(answer), category=category)