def testall():
url = "http://www.zhihu.com/question/24269892"
question = Question(url)
answers = question.get_all_answers()
for answer in answers:
answer.to_txt()
answer.to_md()
def testall():
url = "http://www.zhihu.com/question/24269892"
question = Question(url)
answers = question.get_all_answers()
for answer in answers:
answer.to_txt()
answer.to_md()
def test():
url = "http://www.zhihu.com/question/24269892"
question = Question(url)
# 得到排名第一的答案
answer = question.get_top_answer()
# 得到排名第一的答案的作者
user = answer.get_author()
# 得到该作者回答过的所有问题的答案
user_answers = user.get_answers()
# 输出该作者回答过的所有问题的标题
for answer in user_answers:
print 'answer_url',answer.answer_url
print answer.get_question()
print answer.get_question().get_title()
# 得到该用户的所有收藏夹
user_collections = user.get_collections()
for collection in user_collections:
# 输出每一个收藏夹的名字
print collection.get_name()
# 得到该收藏夹下的前十个回答
top_answers = collection.get_top_i_answers(10)
# 把答案内容转成txt，markdown
for answer in top_answers:
answer.to_txt()
answer.to_md()
def main(): url = "https://www.zhihu.com/question/40935515" question = Question(url) answers = question.get_all_answers() i = 1 for answer in answers: print i i = i+1
def dealWithPage(page_num):
page = urlparse.urljoin(url_prefix, str(page_num))
question_index_filename = 'q_index'
try:
question = Question(page)
except:
print 'Question Get Error.'
return
f = codecs.open(question_index_filename + '.txt', 'a')
f.write(str(page_num) + '\r\n')
f.close()
question_folder = 'Zhihu/Question_' + str(page_num)
question_filename = 'q'
if (not os.path.exists(question_folder)):
os.makedirs(question_folder)
f = codecs.open(os.path.join(question_folder, question_filename + '.txt'),
'w')
f.write(question.get_title() + '\r\n|||\r\n')
f.write(question.get_detail() + '\r\n|||\r\n')
for topic in question.get_topics():
f.write(topic + '\t')
f.write('\r\n|||\r\n')
f.write(str(question.get_visit_times()) + '\r\n|||\r\n')
f.write(str(question.get_followers_num()) + '\r\n|||\r\n')
f.write(str(question.get_answers_num()) + '\r\n|||\r\n')
f.close()
answers = question.get_all_answers()
for answer in answers:
ansURL = answer.answer_url
ans = Answer(ansURL)
answer_folder = os.path.join(question_folder, 'Answer')
answer_filename = str(ansURL.split('/')[-1])
answer_index_filename = 'a_index'
f = codecs.open(answer_index_filename + '.txt', 'a')
f.write(str(page_num) + '|||' + str(answer_filename) + '\r\n')
f.close()
if (not os.path.exists(answer_folder)):
os.makedirs(answer_folder)
f = codecs.open(os.path.join(answer_folder, answer_filename + '.txt'),
'w')
try:
f.write(ans.get_content().find('body').get_text().strip().encode(
"gbk", 'ignore') + '\r\n|||\r\n')
f.write(ans.get_author().get_user_id() + '\r\n|||\r\n')
f.write(str(ans.get_upvote()) + '\r\n|||\r\n')
except:
print 'TimeOut Occurred.'
f.close()
f = codecs.open(
os.path.join(answer_folder, answer_filename + '.txt'), 'w')
f.write('None')
f.close()
continue
f.close()
def setUpClass(cls):
url = 'http://www.zhihu.com/question/24825703'
file_path = os.path.join(TEST_DATA_PATH, 'question.html')
with open(file_path, 'rb') as f:
html = f.read()
soup = BeautifulSoup(html)
cls.question = Question(url)
cls.question._session = None
cls.question.soup = soup
cls.expected = {
'id': 24825703,
'qid': 2112271,
'xsrf': 'cfd489623d34ca03adfdc125368c6426',
'html': soup.prettify(),
'title': '关系亲密的人之间要说「谢谢」吗？',
'details': description,
'answer_num': 621,
'follower_num': 4427,
'top_answer_id': 39753456,
'top_answer_author_name': '芝士就是力量',
'top_answer_upvote_num': 97,
'top_50_ans_id': 31003847,
'top_50_ans_author_name': '圭多达莱佐',
'top_50_ans_upvote_num': 31,
'more_ans_id': 39958704,
'more_ans_author_name': '柳蜻蜓',
'more_ans_upvote_num': 1,
'topics': ['心理学', '恋爱', '社会', '礼仪', '亲密关系'],
}
more_ans_file_path = os.path.join(TEST_DATA_PATH,
'question_more_answer.html')
with open(more_ans_file_path, 'rb') as f:
cls.more_ans_html = f.read()
def exp_question():
q = Question('http://www.zhihu.com/question/29693016')
# 获取问题标签
for tag in q.get_tags:
print tag,
# 校园招聘 实习生 社会招聘 面试技巧 互联网求职
# 获得问题标题
print q.get_question
# 互联网求职路上，你见过哪些写得很好、很用心的面经？最好能分享自己的面经、心路历程。
# 获取问题描述
"""以markdown形式输出"""
print q.ques_description
# 技术类、非技术类的都行；校招、社招的都行。诚然，此问题并不局限于分享面经，也可以授之以渔而非授之以鱼。...
# 获取问题关注者人数
print q.ques_followers
# 关注者人数为1323
# 获取问题回答数
print q.answer_num
# 回答人数为：17
# 获取排在最前面的回答
print q.top_answer
# 第1个答案:
# 自问自答。开这个问题的初衷是希望知乎上的CS大牛们能分享一下自己的求职心路历程，既然大家都这么羞涩，我只好抛砖引玉（一般来说，需要二次跳转查看的答案传播面都不会太广）。
# 获取排名前几位的回答
print q.top_i_answers(2)
# ...
# 第2个答案:
# [@Michael282694](http://www.zhihu.com/people/7303e4f770e8055f3bedc4cf3b192325)说我不回答就要拉黑我，心理感觉到了深深的恐惧（她说她准备了5把刀）
# ...
# 获取所有回答
print q.all_answers
def question_test(self, url):
question = Question(url)
# 获取该问题的标题
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
# answers_num = question.get_answers_num()
# 获取关注该问题的人数
# followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取该问题被浏览次数
# visit_times = question.get_visit_times()
# 获取排名第一的回答
# top_answer = question.get_top_answer()
# 获取排名前十的十个回答
top_answers = question.get_top_i_answers(10)
# 获取所有回答
answers = question.get_all_answers()
# print title # 输出：现实可以有多美好？
# print detail
# 输出：
# 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
# 题主： 昨天看了“现实可以有多残酷“。感觉不太好，所以我
# 开了这个问题以相对应，希望能够“中和一下“。和那个问题题主不想
# 把它变成“比惨大会“一样，我也不想把这个变成“鸡汤故事会“，或者
# 是“晒幸福“比赛。所以大家从“现实，实际”的角度出发，讲述自己的
# 美好故事，让大家看看社会的冷和暖，能更加辨证地看待世界，是此
# 题和彼题共同的“心愿“吧。
# print answers_num # 输出：2441
# print followers_num # 输出：26910
# for topic in topics:
# print type(topic)
# print topic, # 输出：情感克制 现实 社会 个人经历
# print visit_times # 输出: 该问题当前被浏览的次数
# print top_answer # 输出：<zhihu.Answer instance at 0x7f8b6582d0e0>(Answer类对象)
# print top_answers # 输出：<generator object get_top_i_answers at 0x7fed676eb320>(代表前十的Answer的生成器)
# print answers # 输出：<generator object get_all_answer at 0x7f8b66ba30a0>(代表所有Answer的生成器)
answers_list = []
for answer in answers: #top_answers
answers_list.append(answer.to_txt())
if len(answers_list) > 0:
answers = []
topics = json.dumps(topics).decode('unicode-escape').encode('utf8')
time_now = int(time.time())
p_str = 'INSERT IGNORE INTO ANSWER (QURL, TITLE, DETAIL, TOPICS, AURL, USERID, CONTENT, UPVOTE, USERURL, ADD_TIME, LAST_VISIT) VALUES (%s, %s, %s, %s, %s, %s, %s,%s, %s, %s,%s)'
for answer in answers_list:
answers = answers + [
(url, title, detail, topics, answer["aurl"],
answer["userid"], answer["content"], answer["upvote"],
answer["userurl"], time_now, 0)
]
self.cursor.executemany(p_str, answers)
return self.cursor.rowcount
else:
print "no answer"
return 0
def test_follow_question_with_answer_url(self):
"""
也支持回答的URL，因为从回答中也能找到问题的ID
:return:
"""
data = Question(
url='https://www.zhihu.com/question/59001738/answer/160832685'
).follow_question()
self.assertEqual({"is_following": True}, data)
def question(self, url):
question = Question(url)
title = question.get_title() # 标题
detail = question.get_detail() # 描述
answers_num = question.get_answers_num() # 回答个数
followers_num = question.get_followers_num() # 关注人数
topics = question.get_topics() # 所属话题
top_answers = question.get_top_i_answers(10) # 前十回答
return title, detail, answers_num, followers_num, topics, top_answers
def main():
urls = [
"https://www.zhihu.com/topic/19843695"
]
topicquestion = Topicquestion(urls)
topicquestion.execute()
f = open("config/question.list","r")
lines = f.readlines()
for line in lines:
url = "https://www.zhihu.com/question/"+line.strip()
question = Question(url)
answers = question.get_all_answers()
once = True
for answer in answers:
answer.to_sql(line.strip()+'.sql',once,question.get_detail())
once = False
f.close()
def main():
vl = []
viplist = []
qlist = []
fi=open("userlist.txt")
msg = fi.readline()
while msg :
name = msg[0:len(msg)-1]
vl.append(name)
msg=fi.readline()
fi.close()
f1=open("susp/list2.txt")
msg = f1.readline()
while msg :
name = msg[0:len(msg)-1]
viplist.append(name)
msg=f1.readline()
f1.close()
f1=open("susp/questionlist2.txt","r")
msg = f1.readline().strip("\n")
while msg :
print msg
# ques = msg[0:len(msg)-1]
qlist.append(msg)
msg=f1.readline().strip("\n")
f1.close()
print "start"
offset = qlist.index("30008137", )
for qid in qlist[offset:]:
print qid
qfile=open("susp/vext2/"+qid+".txt","w")
qurl="http://www.zhihu.com/question/"+qid
que=Question(qurl)
alist = que.get_all_answers()
for aut in alist:
if aut in vl and aut not in viplist:
print aut
qfile.write(str(vl.index(aut, ))+" "+aut+"\n")
print "finish "+qid+"\n"
def question_test(url):
question = Question(url)
# 获取该问题的标题
# title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取该问题被浏览次数
visit_times = question.get_visit_times()
# 获取排名第一的回答
top_answer = question.get_top_answer()
# 获取排名前十的十个回答
top_answers = question.get_top_i_answers(10)
# 获取所有回答
answers = question.get_all_answers()
# print title # 输出：现实可以有多美好？
print detail
# 输出：
# 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
# 题主： 昨天看了“现实可以有多残酷“。感觉不太好，所以我
# 开了这个问题以相对应，希望能够“中和一下“。和那个问题题主不想
# 把它变成“比惨大会“一样，我也不想把这个变成“鸡汤故事会“，或者
# 是“晒幸福“比赛。所以大家从“现实，实际”的角度出发，讲述自己的
# 美好故事，让大家看看社会的冷和暖，能更加辨证地看待世界，是此
# 题和彼题共同的“心愿“吧。
print answers_num # 输出：2441
print followers_num # 输出：26910
for topic in topics:
print topic, # 输出：情感克制 现实 社会 个人经历
print visit_times # 输出: 该问题当前被浏览的次数
print top_answer # 输出：<zhihu.Answer instance at 0x7f8b6582d0e0>(Answer类对象)
print top_answers # 输出：<generator object get_top_i_answers at 0x7fed676eb320>(代表前十的Answer的生成器)
print answers # 输出：<generator object get_all_answer at 0x7f8b66ba30a0>(代表所有Answer的生成器)
def question_test(url):
question = Question(url)
# 获取该问题的标题
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取该问题被浏览次数
visit_times = question.get_visit_times()
# 获取排名第一的回答
top_answer = question.get_top_answer()
# 获取排名前十的十个回答
top_answers = question.get_top_i_answers(10)
# 获取所有回答
answers = question.get_all_answers()
print title # 输出：现实可以有多美好？
print detail
# 输出：
# 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
# 题主： 昨天看了“现实可以有多残酷“。感觉不太好，所以我
# 开了这个问题以相对应，希望能够“中和一下“。和那个问题题主不想
# 把它变成“比惨大会“一样，我也不想把这个变成“鸡汤故事会“，或者
# 是“晒幸福“比赛。所以大家从“现实，实际”的角度出发，讲述自己的
# 美好故事，让大家看看社会的冷和暖，能更加辨证地看待世界，是此
# 题和彼题共同的“心愿“吧。
print answers_num # 输出：2441
print followers_num # 输出：26910
for topic in topics:
print topic, # 输出：情感克制 现实 社会 个人经历
print visit_times # 输出: 该问题当前被浏览的次数
print top_answer # 输出：<zhihu.Answer instance at 0x7f8b6582d0e0>(Answer类对象)
print top_answers # 输出：<generator object get_top_i_answers at 0x7fed676eb320>(代表前十的Answer的生成器)
print answers # 输出：<generator object get_all_answer at 0x7f8b66ba30a0>(代表所有Answer的生成器)
def test():
url = "http://www.zhihu.com/question/24269892"
question = Question(url)
# 得到排名第一的答案
answer = question.get_top_answer()
# 得到排名第一的答案的作者
user = answer.get_author()
# 得到该作者回答过的所有问题的答案
user_answers = user.get_answers()
# 输出该作者回答过的所有问题的标题
for answer in user_answers:
print answer.get_question().get_title()
# 得到该用户的所有收藏夹
user_collections = user.get_collections()
for collection in user_collections:
# 输出每一个收藏夹的名字
print collection.get_name()
# 得到该收藏夹下的前十个回答
top_answers = collection.get_top_i_answers(10)
# 把答案内容转成txt，markdown
for answer in top_answers:
answer.to_txt()
answer.to_md()
def setUpClass(cls):
url = 'http://www.zhihu.com/question/24825703'
file_path = os.path.join(TEST_DATA_PATH, 'question.html')
with open(file_path, 'rb') as f:
html = f.read()
soup = BeautifulSoup(html)
cls.question = Question(url)
cls.question._session = None
cls.question.soup = soup
act_time = datetime.datetime.fromtimestamp(1439395600)
act_type = ActType.FOLLOW_QUESTION
cls.activity = Activity(act_type, act_time, question=cls.question)
def question_test(url):
print "looking "+url
question = Question(url)
# 获取该问题的标题
if question.isInvalid():
# print 'invalid '+url
return
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
# followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取该问题被浏览次数
visit_times = question.get_visit_times()
# 获取排名第一的回答
top_answer = question.get_top_answer()
# 获取排名前十的十个回答
top_answers = question.get_top_i_answers(10)
# 获取所有回答
answers = question.get_all_answers()
for answer in top_answers:
read=file("folder/a.txt","a+");
if answer.get_upvote()>1000:
print answer.get_upvote(),answer.answer_url
read.write("\r\n"+url+"\r\n"+title+"--"+answer.get_author().get_user_id()+"\r\n"+"%d"%answer.get_upvote()+"\r\n")
read.close()
def question(self, url):
question = Question(url)
# 获取该问题的标题
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取排名第一的回答
# top_answer = question.get_top_answer()
# 获取排名前十的十个回答
top_answers = question.get_top_i_answers(10)
# 获取所有回答
# answers = question.get_all_answers()
# print title # 输出：现实可以有多美好？
# print detail
# # 输出：
# # 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
# # 题主： 昨天看了“现实可以有多残酷“。感觉不太好，所以我
# # 开了这个问题以相对应，希望能够“中和一下“。和那个问题题主不想
# # 把它变成“比惨大会“一样，我也不想把这个变成“鸡汤故事会“，或者
# # 是“晒幸福“比赛。所以大家从“现实，实际”的角度出发，讲述自己的
# # 美好故事，让大家看看社会的冷和暖，能更加辨证地看待世界，是此
# # 题和彼题共同的“心愿“吧。
# print answers_num # 输出：2441
# print followers_num # 输出：26910
# for topic in topics:
# print topic , # 输出：情感克制 现实 社会 个人经历
# print top_answer # 输出：<zhihu.Answer instance at 0x7f8b6582d0e0>（Answer类对象）
# print top_answers # 输出：<generator object get_top_i_answers at 0x7fed676eb320>（代表前十的Answer的生成器）
# print answers # 输出：<generator object get_all_answer at 0x7f8b66ba30a0>（代表所有Answer的生成器）
return title, detail, answers_num, followers_num, topics, top_answers
def question_test(url):
question = Question(url)
# 获取该问题的标题
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取该问题被浏览次数
visit_times = question.get_visit_times()
# 获取排名第一的回答
# top_answer = question.get_top_answer()
# 获取排名前十的十个回答
# top_answers = question.get_top_i_answers(10)
# 获取所有回答
# answers = question.get_all_answers()
print title # 输出：现实可以有多美好？
print detail
# 输出：
# 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
# 题主： 昨天看了“现实可以有多残酷“。感觉不太好，所以我
# 开了这个问题以相对应，希望能够“中和一下“。和那个问题题主不想
# 把它变成“比惨大会“一样，我也不想把这个变成“鸡汤故事会“，或者
# 是“晒幸福“比赛。所以大家从“现实，实际”的角度出发，讲述自己的
# 美好故事，让大家看看社会的冷和暖，能更加辨证地看待世界，是此
# 题和彼题共同的“心愿“吧。
print answers_num # 输出：2441
print followers_num # 输出：26910
for topic in topics:
print topic, # 输出：情感克制 现实 社会 个人经历
print visit_times # 输出: 该问题当前被浏览的次数
def question(self, url):
question = Question(url)
# 获取该问题的标题
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
followers_num = question.get_followers_num()
# 获取该问题所属话题
topics = question.get_topics()
# 获取排名第一的回答
# top_answer = question.get_top_answer()
# 获取排名前十的十个回答
top_answers = question.get_top_i_answers(10)
# 获取所有回答
# answers = question.get_all_answers()
# print title # 输出：现实可以有多美好？
# print detail
# # 输出：
# # 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
# # 题主： 昨天看了“现实可以有多残酷“。感觉不太好，所以我
# # 开了这个问题以相对应，希望能够“中和一下“。和那个问题题主不想
# # 把它变成“比惨大会“一样，我也不想把这个变成“鸡汤故事会“，或者
# # 是“晒幸福“比赛。所以大家从“现实，实际”的角度出发，讲述自己的
# # 美好故事，让大家看看社会的冷和暖，能更加辨证地看待世界，是此
# # 题和彼题共同的“心愿“吧。
# print answers_num # 输出：2441
# print followers_num # 输出：26910
# for topic in topics:
# print topic , # 输出：情感克制 现实 社会 个人经历
# print top_answer # 输出：<zhihu.Answer instance at 0x7f8b6582d0e0>（Answer类对象）
# print top_answers # 输出：<generator object get_top_i_answers at 0x7fed676eb320>（代表前十的Answer的生成器）
# print answers # 输出：<generator object get_all_answer at 0x7f8b66ba30a0>（代表所有Answer的生成器）
return title, detail, answers_num, followers_num, topics, top_answers
def test_follow_question_with_id(self):
data = Question(id=32096743).follow_question()
self.assertEqual({"is_following": True}, data)
def test_follow_question_with_id(self):
data = Question(id=32096743).follow_question()
self.assertIn("is_following", data)
self.assertIn("true", data)
def test_unfollow_question_with_url(self):
data = Question(
url='https://www.zhihu.com/question/58684385').unfollow_question()
self.assertEqual('', data)
def test_follow_question_with_url(self):
data = Question(
url='https://www.zhihu.com/question/58684385').follow_question()
self.assertIn("is_following", data)
self.assertIn("true", data)
def test_unfollow_question_with_id(self):
data = Question(id=32096743).unfollow_question()
self.assertEqual('', data)
# -*- coding: utf-8 -*- from zhihu import Question url = "http://www.zhihu.com/question/24269892" question = Question(url) # 获取该问题的标题 title = question.get_title() # 获取该问题的详细描述 detail = question.get_detail() # 获取回答个数 answers_num = question.get_answers_num() # 获取关注该问题的人数 followers_num = question.get_followers_num() # 获取该问题所属话题 topics = question.get_topics() # 获取该问题被浏览次数 visit_times = question.get_visit_times() # 获取排名第一的回答 top_answer = question.get_top_answer() # 获取排名前十的十个回答 top_answers = question.get_top_i_answers(100) # 获取所有回答 answers = question.get_all_answers() print "Title: " print title # 输出：现实可以有多美好？ print "Detail: " print detail # 输出： # 本问题相对于“现实可以多残酷？传送门：现实可以有多残酷？
from zhihu import Zhihu
z = Zhihu()
z.user(user_slug="liuzhijun001")
def vote_up_with_id():
data = Answer(id=14005147).vote_up()
print(data)
logging.basicConfig(level=logging.INFO)
if __name__ == '__main__':
# vote_up_with_id()
from zhihu import Question
Question(id="60231684").unfollow_question()
# Zhihu().login("+33752962193", "zhihudetail")
# model.login("158", "xxxx")
# from zhihu import Zhihu
#
# profile = Zhihu().user(user_slug="xiaoxiaodouzi")
# # print(profile)
#
# from zhihu import Account
#
# account = Account()
# account.register("续航小三", phone_num="+33752962193", password="******")
from zhihu import User, UserDetail, Question
user = UserDetail("https://www.zhihu.com/people/lan-jiang-26")
t = user.get_followees()
user.get_followees_num()
# print(user.get_user_id())
print(user.get_data_id())
print(user.get_gender())
print(user.get_followees_num())
print(user.get_followers_num())
print(user.get_agree_num())
print(user.get_thanks_num())
print(user.get_asks_num())
print(user.get_answers_num())
print(user.get_collections_num())
print(user.get_profile_vote_num())
print(user.get_profile_thank_num())
print(user.get_profile_fav_num())
print(user.get_followers())
# for user in user.get_followers():
# print(user)
t = user.get_topics()
for tt in t:
print(tt.name)
print(tt.id)
question = Question(url='https://www.zhihu.com/question/32046716')
print(question.get_detail())
print(question.get_topics())
def download_answers(urls, topic_id, log_fname):
answer_file_name = "Answers_text_" + topic_id + ".txt"
# Open a file to store all answers
if not os.path.exists(os.path.join(os.getcwd(), answer_file_name)):
out_answer_text = open(answer_file_name, "w")
out_answer_text.close()
for i in range(0, len(urls)):
url = urls[i]
print url
question = Question('http://www.zhihu.com' + url)
# 获取该问题的标题
title = question.get_title()
# 获取该问题的详细描述
detail = question.get_detail()
# 获取回答个数
answers_num = question.get_answers_num()
# 获取关注该问题的人数
# try:
# followers_num = question.get_followers_num()
# except:
# followers_num = 0
# 获取该问题所属话题
topics = question.get_topics()
# 获取该问题被浏览次数
# visit_times = question.get_visit_times()
# 获取排名第一的回答
# top_answer = question.get_top_answer()
# 获取排名前十的十个回答
# top_answers = question.get_top_i_answers(10)
# 获取所有回答
answers = question.get_all_answers()
print "============"
print "问题: \n", title
print "问题描述: \n", detail
print "Number of Answers: ", answers_num
# print followers_num
for topic in topics:
print topic,
# print visit_times
# print top_answer
# print top_answers
print answers
out_answer_text = open(answer_file_name, "a")
this_question_answers_text = []
for answer in answers:
author = answer.get_author()
answer_cleaned = answer.text_one_line()
print answer_cleaned
this_question_answers_text.append(answer_cleaned)
# answer.to_txt(title, detail, answers_num, followers_num, topics, visit_times, author)
# t_sleep = random.uniform(2,4) # Stop after scraping one page.
# print termcolor.colored(' '.join(['Sleep Time: ', str(t_sleep)]), "white")
# time.sleep(t_sleep)
# print "\n"
out_answer_text.write("".join(this_question_answers_text))
# Modify log file after successfully write the answers
log_file = open(log_fname, "w")
log_file.write("\n".join(urls[i:]))
print termcolor.colored("Log modified.", "white")
# Stop after scraping one page.
print "\n--------------\n--------------"
t_sleep = random.uniform(1, 2)
print termcolor.colored(' '.join(['Sleep Time: ',
str(t_sleep)]), "red")
time.sleep(t_sleep)
out_answer_text.close()
def __init__(self, question_id):
self.question_id = question_id
que = Question(prefix_question + question_id)
self.topics = que.get_topics()
def test_follow_question_with_url(self):
data = Question(
url='https://www.zhihu.com/question/58684385').follow_question()
self.assertEqual({"is_following": True}, data)
def __init__(self, question_id):
self.question_id = question_id
que = Question(prefix_question + question_id)
self.topics = que.get_topics()
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from zhihu import Question
url = "http://www.zhihu.com/question/25378124"
question = Question(url)
answers = question.get_all_answers()
for answer in answers:
answer.to_txt()
answer.to_md()
