def answer_test(answer_url):
answer = Answer(answer_url)
# 获取该答案回答的问题
question = answer.get_question()
# 获取该答案的作者
author = answer.get_author()
# 获取该答案获得的赞同数
upvote = answer.get_upvote()
# 获取改该答案所属问题被浏览次数
visit_times = answer.get_visit_times()
# 获取所有给该答案点赞的用户信息
voters = answer.get_voters()
# 把答案输出为txt文件
answer.to_txt()
# 把答案输出为markdown文件
answer.to_md()
print question
# <zhihu.Question instance at 0x7f0b25d13f80>
# 一个Question对象
print question.get_title() # 输出：现实可以有多美好？
print author
# <zhihu.User instance at 0x7f0b25425b90>
# 一个User对象
print voters # <generator object get_voters at 0x7f32fbe55730>(代表所有该答案点赞的用户的生成器)
print author.get_user_id() # 输出：田浩
print upvote # 输出：9320
print visit_times # 输出: 改答案所属问题被浏览次数
def answer_test(answer_url):
answer = Answer(answer_url)
# 获取该答案回答的问题
question = answer.get_question()
# 获取该答案的作者
author = answer.get_author()
# 获取该答案获得的赞同数
upvote = answer.get_upvote()
# 获取改该答案所属问题被浏览次数
visit_times = answer.get_visit_times()
# 获取所有给该答案点赞的用户信息
voters = answer.get_voters()
# 把答案输出为txt文件
answer.to_txt()
# 把答案输出为markdown文件
answer.to_md()
print question
# <zhihu.Question instance at 0x7f0b25d13f80>
# 一个Question对象
print question.get_title() # 输出：现实可以有多美好？
print author
# <zhihu.User instance at 0x7f0b25425b90>
# 一个User对象
print voters # <generator object get_voters at 0x7f32fbe55730>(代表所有该答案点赞的用户的生成器)
print author.get_user_id() # 输出：田浩
print upvote # 输出：9320
print visit_times # 输出: 改答案所属问题被浏览次数
def answer_test(answer_url):
answer = Answer(answer_url)
# 获取该答案回答的问题
question = answer.get_question()
# 获取该答案的作者
author = answer.get_author()
# 获取该答案获得的赞同数
upvote = answer.get_upvote()
# 获取改该答案所属问题被浏览次数
visit_times = answer.get_visit_times()
# 获取所有给该答案点赞的用户信息
voters = answer.get_voters()
# 获取答案长度
answer_length = answer.get_answer_length()
# 把答案输出为txt文件
answer.to_txt()
# 把答案输出为markdown文件
answer.to_md()
print question
# <zhihu.Question instance at 0x7f0b25d13f80>
# 一个Question对象
print question.get_title() # 输出：现实可以有多美好？
print author
# <zhihu.User instance at 0x7f0b25425b90>
# 一个User对象
for voter in voters:
print voter
# 一个 User 对象
print author.get_user_id() # 输出：田浩
print upvote # 输出：9320
print visit_times # 输出: 改答案所属问题被浏览次数
print 'answer_length', answer_length # 输出:
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 answer_test(answer_url):
answer = Answer(answer_url)
# 获取该答案回答的问题
question = answer.get_question()
# 获取该答案的作者
author = answer.get_author()
# 获取该答案获得的赞同数
upvote = answer.get_upvote()
# 把答案输出为txt文件
answer.to_txt()
# 把答案输出为markdown文件
answer.to_md()
print question
# <zhihu.Question instance at 0x7f0b25d13f80>
# 一个Question对象
print question.get_title() # 输出：现实可以有多美好？
print author
# <zhihu.User instance at 0x7f0b25425b90>
# 一个User对象
print author.get_user_id() # 输出：田浩
print upvote # 输出：9320
def answer_test(answer_url):
answer = Answer(answer_url)
# 获取该答案回答的问题
question = answer.get_question()
# 获取该答案的作者
author = answer.get_author()
# 获取该答案获得的赞同数
upvote = answer.get_upvote()
# 把答案输出为txt文件
answer.to_txt()
# 把答案输出为markdown文件
answer.to_md()
print question
# <zhihu.Question instance at 0x7f0b25d13f80>
# 一个Question对象
print question.get_title() # 输出：现实可以有多美好？
print author
# <zhihu.User instance at 0x7f0b25425b90>
# 一个User对象
print author.get_user_id() # 输出：田浩
print upvote # 输出：9320
# -*- coding: utf-8 -*- from zhihu import Answer answer_url = "http://www.zhihu.com/question/24269892/answer/29960616" answer = Answer(answer_url) # 获取该答案回答的问题 question = answer.get_question() # 获取该答案的作者 author = answer.get_author() # 获取该答案获得的赞同数 upvote = answer.get_upvote() # 获取该答案所属问题被浏览次数 visit_times = answer.get_visit_times() # 获取所有给该答案点赞的用户信息 voters = answer.get_voters() # 把答案输出为txt文件 answer.to_txt() # 把答案输出为markdown文件 answer.to_md() print question # <zhihu.Question instance at 0x7f0b25d13f80> # 一个Question对象 print question.get_title() # 输出：现实可以有多美好？ print author # <zhihu.User instance at 0x7f0b25425b90> # 一个User对象 print voters # <generator object get_voters at 0x7f32fbe55730> # 代表所有该答案点赞的用户的生成器 print author.get_user_id() # 输出：田浩
