Exemplo n.º 1
0
i = 0
saved_num = 17406

for user in users:
    print i,user
    i += 1
    if i < saved_num:
        continue
    else:
        if User(user).asks_num()!=0:
            j = 0
            try:
                questions = User(user).get_asks()
                for question in questions:
                    if question.url not in pool_questions:
                        if page_exist(question.url):
                            url = question.url
                            tmp = Question(url)
                            try:
                                db.insert_question(tmp.get_title(),url,tmp.get_followers_num(),tmp.get_answers_num(),tmp.get_detail())
                                j += 1
                            except Exception as e:
                                print question.url,e
                        else:
                            print question.url+"404 not found"
                        pool_questions.add(question.url)
            except Exception as e:
                print user,e
            print ("saved %d new questions" % j)
        else:
            print "no questions"
Exemplo n.º 2
0
pool_answers = db.get_existing("answers")
i = 1
saved_num = 1277

for user in users:
    print i,user
    i += 1
    if i < saved_num :
        continue
    else:
        if User(user).answers_num()!=0:
            j = 0
            answers = User(user).get_answers()
            for answer in answers:
                if answer.answer_url not in pool_answers:
                    if page_exist(answer.answer_url):
                        url = answer.answer_url
                        tmp = Answer(url)
                        if tmp.get_content()!= None:
                            try:
                                db.insert_answer(tmp.answer_url,tmp.get_author(),tmp.get_content(),tmp.get_upvote(),tmp.get_question())
                                j += 1
                            except Exception as e:
                                print  answer.answer_url,e
                        else:
                            print answer.answer_url+"被折叠"
                    else:
                        print answer.answer_url+"404 not found"
                    pool_answers.add(answer.answer_url)
            print ("saved %d new answers" % j)