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 parse_article(self, response):
self.parse_article_count += 1
Logging.info('======================%d' % self.parse_article_count)
Logging.info(response.url)
answer = Answer(response)
Logging.info('author: %s' % answer.author())
(contents, img_urls) = answer.content()
Logging.info(contents)
index = 0
for url in img_urls:
index += 1
Logging.info(url)
r = requests.get(url)
if not os.path.exists('pic'):
os.system('mkdir pic/')
file_name = 'pic/' + answer.author() + '%d' % index + '.png'
if r.status_code == 200:
with open(file_name, 'w+') as f:
f.write(r.content)
f.close()
return
def test_vote_up_with_url(self):
time.sleep(1)
answer = Answer(url="https://www.zhihu.com/question/19761434/answer/14005147")
data = answer.vote_up()
self.assertEqual("14005147", answer.id)
self.assertIn("voting", data)
self.assertIn("voteup_count", data)
def main():
viplist = []
qlist=[]
f1=open("userlist.txt","r")
msg = f1.readline()
while msg :
print msg
name = msg[0:len(msg)-1]
viplist.append(name)
msg=f1.readline()
f1.close()
f1=open("questionlist-filtered.txt","r")
msg = f1.readline().strip("\n")
while msg :
print msg
qlist.append(msg)
msg=f1.readline().strip("\n")
f1.close()
offset = qlist.index("37344024")
# offset = qlist.index("30014729", )
for qid in qlist[offset:]:
alist=[]
autlist=[]
qfile=open("question/"+qid+".txt","r")
vfile=open("ansupv/"+qid+".txt","w")
print "question/"+qid+".txt"
line=qfile.readline().strip("\n")
while line :
ainfo = line.split(" ")
autlist.append(ainfo[0])
alist.append(ainfo[2])
line=qfile.readline().strip("\n")
qfile.close()
urlpref="http://www.zhihu.com/question/"+qid
auts = 0
for aid in alist:
vcount= 0
vlist=[]
if qid=="33554687" and aid == "56818808":
continue
ans = Answer(urlpref+"/answer/"+aid)
print ans.answer_url
ansvoters = ans.get_voters()
for v in ansvoters:
if v in viplist :
print vcount
print v
vlist.append(v)
vcount=vcount+1
vfile.write(aid+" "+str(autlist[auts])+" "+str(vcount)+"\n")
auts = auts+1
for vt in vlist:
vfile.write(vt+"\n")
vfile.close
print "finish "+qid
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 test_nothelp_cancel_with_url(self):
time.sleep(1)
data = Answer(
url="https://www.zhihu.com/question/19761434/answer/14005147"
).thank_cancel()
self.assertIn("is_thanked", data)
self.assertEqual({"is_nothelp": False}, data)
def test_vote_neutral_with_url(self):
time.sleep(1)
data = Answer(
url="https://www.zhihu.com/question/19761434/answer/14005147"
).vote_neutral()
self.assertIn("voting", data)
self.assertIn("voteup_count", data)
def test_thank_with_url(self):
time.sleep(1)
data = Answer(
url="https://www.zhihu.com/question/19761434/answer/14005147"
).thank()
self.assertIn("is_thanked", data)
self.assertIn("true", data)
def setUpClass(cls):
url = 'http://www.zhihu.com/question/24825703/answer/30975949'
file_path = os.path.join(TEST_DATA_PATH, 'answer.html')
with open(file_path, 'rb') as f:
html = f.read()
soup = BeautifulSoup(html)
answer_saved_path = os.path.join(TEST_DATA_PATH, 'answer.md')
with open(answer_saved_path, 'rb') as f:
cls.answer_saved = f.read()
cls.answer = Answer(url)
cls.answer._session = None
cls.answer.soup = soup
cls.expected = {
'id': 30975949,
'aid': 7775236,
'xsrf': 'cfd489623d34ca03adfdc125368c6426',
'html': soup.prettify(),
'author_id': 'tian-ge-xia',
'author_name': '甜阁下',
'question_id': 24825703,
'question_title': '关系亲密的人之间要说「谢谢」吗？',
'upvote_num': 1164,
'upvoter_name': 'Mikuroneko',
'upvoter_id': 'guo-yi-hui-23'
}
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
def test_images(self):
Answer(url="https://www.zhihu.com/question/58481349/answer/184247410"
).images()
def test_nothelp_with_url(self):
time.sleep(1)
data = Answer(
url="https://www.zhihu.com/question/19761434/answer/14005147"
).thank()
self.assertEqual({"is_nothelp": True}, data)
def test_vote_down_with_id(self):
time.sleep(1)
data = Answer(id=14005147).vote_down()
self.assertIn("voting", data)
self.assertIn("voteup_count", data)
def vote_up_with_id():
data = Answer(id=14005147).vote_up()
print(data)
import requests.utils import pickle from http.cookies import SimpleCookie from zhihu import Zhihu from zhihu import Answer zhihu = Zhihu() # print(zhihu.cookies) # 查看用户profile 成功 # profile = zhihu.profile(user_slug="xiaoxiaodouzi") # print(profile) # 发送私信 成功 # response = zhihu.send_message(content='TESTMESSAGE', user_slug="xiaoxiaodouzi") # print(response) # 关注用户 成功 # response = zhihu.follow(user_slug='SemitLee') # print(response) answer = Answer(url="https://www.zhihu.com/question/34401174/answer/389502954") r = answer.images(path="images") # print(r) # 赞同答案 成功 response = answer.vote_neutral() answer.thank_cancel() # print(response)
def test_vote_up_with_id(self):
data = Answer(id=14005147).vote_up()
self.assertIn("voting", data)
self.assertIn("voteup_count", data)
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 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
# -*- 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
# -*- coding: utf-8 -*-
from zhihu import Question
from zhihu import Answer
from zhihu import User
from zhihu import Collection
import requests
url = "https://www.zhihu.com/question/19550321/answer/14240492"
ans = Answer(url)
print ans.get_content().find('body').get_text()
input()
from zhihu import Answer answer = Answer(url="https://www.zhihu.com/question/30913458/answer/193839736") images = answer.images() print(images)
