def parse_author(command):
result = Match.author(command)
author_id = result.group('author_id')
task = SingleTask()
task.kind = 'author'
task.spider.href = 'https://www.zhihu.com/people/{}'.format(author_id)
task.book.kind = 'author'
client = ZhihuClient()
try:
client.load_token(Path.pwd_path + str(u'/ZHIHUTOKEN.pkl'))
except IOError:
print u"没有找到登录信息文件，请先登录"
sys.exit()
except NeedLoginException:
print u"登录信息过期，请重新登录"
sys.exit()
people_oauth = client.people(author_id)
_ = people_oauth.follower_count # zhihu-oauth, issues #4
author_id_hash = people_oauth.id
task.book.sql.info = 'select * from AuthorInfo where author_id = "{}"'.format(author_id_hash)
task.book.sql.question = 'select * from Question where question_id in (select question_id from \
Answer where author_id = "{}")'.format(author_id_hash)
task.book.sql.answer = 'select * from Answer where author_id = "{}"'.format(author_id_hash)
return task
def crawling(id):
#id为问题id
client = ZhihuClient()
# 登录
client.load_token('token.pkl') # 加载token文件
question = client.question(id)
print(u"问题:", question.title)
print(u"回答数量:", question.answer_count)
if not os.path.exists(question.title):
os.mkdir(question.title)
path = question.title
index = 1 # 图片序号
for i, answer in enumerate(question.answers):
content = answer.content # 回答内容
anther = answer.author.name
re_compile = re.compile(
r'<img src="(https://pic\d\.zhimg\.com/.*?\.(jpg|png))".*?>')
img_lists = re.findall(re_compile, content)
if (img_lists):
for img in img_lists:
img_url = img[0] # 图片url
image_name = anther + '_' + str(index) + '.jpg'
if not os.path.exists(path + '/' + image_name):
urllib.request.urlretrieve(img_url,
path + '/' + image_name)
print(u"成功保存第%d张图片:%s,当前总进度%.2f%%" %
(index, image_name, i / question.answer_count * 100))
index += 1
print('第%d个答案爬取完成,当前总进度%.2f%%' % (i, i / question.answer_count * 100))
def download(cid):
client = ZhihuClient()
client.load_token('token.pk1') # 登陆
column = client.column(cid)
images_dir = os.path.join(column.title, 'images')
regex = re.compile(r"https://pic\d.zhimg.com/", re.IGNORECASE)
if not os.path.exists(column.title):
os.makedirs(column.title)
if not os.path.exists(images_dir):
os.makedirs(images_dir)
for index, article in enumerate(column.articles):
# 处理文章
article_f = dealArticle(article)
# 下载图片
downloadImg(article_f['content'], images_dir)
# 替换图片路径
article_f['content'] = re.sub(regex, './images/', article_f['content'])
# 写入
with open(os.path.join(column.title, article_f['title']), 'w+') as f:
f.write(article_f['content'])
print('[%s] download %s success!' % (str(index), article.title))
def prepare(self):
if not os.path.isdir(self.data_path): os.makedirs(self.data_path)
if os.path.isfile(self.friends_file):
with open(self.friends_file, "rb") as f:
self.name_map = pickle.load(f)
else:
self.name_map = dict()
self.client = ZhihuClient()
def __init__(self, dbname,email,key):
self.con = sqlite3.connect(dbname)
self.cursor = self.con.cursor()
TOKEN_FILE = 'token.pkl'
self.zhclient = ZhihuClient()
try:
# self.zhclient.login_in_terminal(email, key)
self.zhclient.login(email, key)
except NeedCaptchaException:
print("需要输入验证码，账号 %s 可能已失效" %(email))
def login_zhihu(self):
"""
登录知乎
:return:
"""
self.client = ZhihuClient()
if os.path.isfile(self.TOKEN_FILE):
self.client.load_token(self.TOKEN_FILE)
else:
self.client.login_in_terminal()
self.client.save_token(self.TOKEN_FILE)
def main():
#login
client = ZhihuClient()
log_in(client)
Image('./a.gif')
captcha = input('please input captcha:')
client.login('account', 'psw', captcha)
get_data(client)
write_hk_student_info()
write_modules()
def LoginZhihuClient(token_name):
TOKEN_FILE = 'liuximing.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
me = client.me()
return me
def getLatestBestAnserwerAndSave():
# phoneNum = '+8613096348217'
# pw = '2015141463222'
ans_num = 20
i=0
TOKEN_FILE = 'token.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
# try:
# client.login(phoneNum, pw)
# except NeedCaptchaException:
# # 保存验证码并提示输入，重新登录
# with open('a.gif', 'wb') as f:
# f.write(client.get_captcha())
# captcha = input('please input captcha:')
# client.login(phoneNum, pw, captcha)
java = client.topic(19550867)
BA = java.best_answers
for answ in BA:
ansItem2artical(ansItem(answ)).save()
i = i+1
if i==ans_num:
break
def login():
client = ZhihuClient()
# try:
# client.login('username', 'password')
# except NeedCaptchaException:
# # 保存验证码并提示输入，重新登录
# with open('a.gif', 'wb') as f:
# f.write(client.get_captcha())
# captcha = input('please input captcha:')
# client.login('email_or_phone', 'password', captcha)
# client.save_token('token.pkl')
client.load_token('/Users/huangyukun/scripts/token.pkl')
return client
def zhihu_login():
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login('*****@*****.**', 'a4906639')
client.save_token(TOKEN_FILE)
me = client.me()
print(me.name)
return client
def setUp(self):
super(ZhihuClientClassTest, self).setUp()
if not os.path.isdir('test') and os.path.isfile('token.pkl'):
os.chdir('..')
if not os.path.isfile('test/token.pkl'):
print('\nno token file, skip all tests.')
self.skipTest('no token file.')
self.client = ZhihuClient()
try:
self.client.load_token('test/token.pkl')
except ValueError:
print('\ntoken version not math python version, skip all tests.')
self.skipTest('token version not math python version.')
def login(username, password):
from zhihu_oauth import ZhihuClient
from zhihu_oauth.exception import NeedCaptchaException
client = ZhihuClient()
try:
client.login(username, password)
print(u"登陆成功!")
except NeedCaptchaException: # 处理要验证码的情况
# 保存验证码并提示输入，重新登录
with open('a.gif', 'wb') as f:
f.write(client.get_captcha())
captcha = input('please input captcha:')
client.login(username, password, captcha)
client.save_token('token.pkl') # 保存token
class TopicTree:
client = ZhihuClient()
def __init__(self):
pass
def login(self):
if os.path.isfile(TOKEN_FILE):
self.client.load_token(TOKEN_FILE)
else:
self.client.login_in_terminal(username='******',
password=self.getpass())
self.client.save_token(TOKEN_FILE)
def login_next(self):
self.client.login_in_terminal(username='******',
password=self.getpass())
def test(self):
me = self.client.me()
print('name', me.name)
def get_topic(self, uid):
topic = self.client.topic(uid)
topic_dic = {}
topic_dic['id'] = uid
topic_dic['name'] = topic.name
topic_dic['children'] = [{
'id': item._id,
'name': item.name
} for item in topic.children]
with open(out_path, 'a', encoding='utf-8') as fw:
json.dump(topic_dic, fw, ensure_ascii=False, sort_keys=True)
fw.write('\n')
for item in topic_dic['children']:
cid = item['id']
try:
self.get_topic(cid)
time.sleep(random.random())
except Exception as e:
traceback.print_exc()
print('ban: ', cid)
self.run(cid)
def run(self, uid):
self.login_next()
self.get_topic(uid)
def getpass(self):
# with open('C:\\Users\\BaoQiang\\Desktop\\password.txt', 'r') as f:
with open('/mnt/home/baoqiang/password.txt', 'r') as f:
return f.read().strip()
def Analyse(self):
client = ZhihuClient()
self.aa.denglu(client)
self.aa.findquestion(client)
print'------------find','\n'
list_q = self.aa.Analyse_question(self.aa.dic_name)
print'----------q','\n'
self.aa.Analyse_answer(list_q)#最慢
print'-------------a','\n'
def login(self):
TOKEN_FILE = 'token.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
return client
def zhihu_login():
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login('*****@*****.**', 'a4906639')
client.save_token(TOKEN_FILE)
me = client.me()
print(me.name)
return client
def setUp(self):
super(ZhihuClientClassTest, self).setUp()
if not os.path.isdir('test') and os.path.isfile(TOKEN_FILE_NAME):
os.chdir('..')
token_file_path = os.path.join('test', TOKEN_FILE_NAME)
if not os.path.isfile(token_file_path):
print('\nno token file, skip all tests.')
self.skipTest('no token file.')
self.client = ZhihuClient()
try:
self.client.load_token(token_file_path)
except ValueError:
print('\ntoken version not math python version, skip all tests.')
self.skipTest('token version not math python version.')
class ZhihuClientClassTest(unittest.TestCase):
def setUp(self):
super(ZhihuClientClassTest, self).setUp()
if not os.path.isdir('test') and os.path.isfile('token.pkl'):
os.chdir('..')
if not os.path.isfile('test/token.pkl'):
print('\nno token file, skip all tests.')
self.skipTest('no token file.')
self.client = ZhihuClient()
try:
self.client.load_token('test/token.pkl')
except ValueError:
print(
'\ntoken version not math python version, skip all tests.')
self.skipTest('token version not math python version.')
def zhihu_login():
r"""
知乎登陆
:return: 登陆之后的客户端client
"""
client = ZhihuClient()
# 登录
if os.path.isfile(TOKEN_FILE_NAME):
client.load_token(TOKEN_FILE_NAME)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE_NAME)
return client
def download(uid):
client = ZhihuClient()
client.load_token('token.pk1') # 登陆
people = client.people(uid)
for index, answer in enumerate(people.answers):
# 下载图片
downloadImg(answer.content)
# 处理文本
article = dealArticle(answer)
# 写入本地
if not os.path.exists(uid):
os.makedirs(uid)
with open(os.path.join(uid, article['title']), 'w+') as f:
f.write(article['content'])
print('[%s] download %s success!' %
(str(index), answer.question.title))
class ZhihuClientClassTest(unittest.TestCase):
def setUp(self):
super(ZhihuClientClassTest, self).setUp()
if not os.path.isdir('test') and os.path.isfile(TOKEN_FILE_NAME):
os.chdir('..')
token_file_path = os.path.join('test', TOKEN_FILE_NAME)
if not os.path.isfile(token_file_path):
print('\nno token file, skip all tests.')
self.skipTest('no token file.')
self.client = ZhihuClient()
try:
self.client.load_token(token_file_path)
except ValueError:
print(
'\ntoken version not math python version, skip all tests.')
self.skipTest('token version not math python version.')
def main():
client = ZhihuClient()
try:
# client.login(email_or_phone, password)
client.login_in_terminal(username=email_or_phone, password=password)
client.save_token(TOKEN_FILE) # 保存登录会话,留着以后登录用
# raise NeedCaptchaException
except NeedCaptchaException:
# 保存验证码并提示输入，重新登录
with open('a.gif', 'wb') as f:
f.write(client.get_captcha())
captcha = input('请输入验证码: ')
client.login(email_or_phone, password, captcha)
data_out_list_a = []
line_saved = 0
max_lines = 1
with open(USER_CSV_PATH) as file:
for line in file.readlines():
crawl_id = line.strip('\n')
my_crawl = MyCrawler(crawl_id, client)
print('------>>>| 待爬取的用户的知乎id为: ', crawl_id)
data_a = my_crawl.crawling_answer(crawl_id)
print('该用户爬取完毕'.center(60, '*'))
if len(data_a) % 60 == 0:
tmp_time = int(len(data_a) / 60)
for i in range(tmp_time):
data_out_list_a.append(data_a[60*i:60*(i+1)])
else:
print('无用的输出!')
# sleep(randint(1, 3))
line_saved += 1
if line_saved == max_lines:
save_to_csv_a(data_out_list_a, client)
data_out_list_a = []
line_saved = 0
print('全部用户采集完毕'.center(40, '*'))
def start(self):
try:
client = ZhihuClient()
client.login_in_terminal()
client.save_token(Path.ZHIHUTOKEN)
except NeedLoginException:
print u"Oops, please try again."
sys.exit()
return
class Login():
def __init__(self):
self.TOKEN_FILE = 'token.pkl.' + str(sys.version_info[0])
self.client = ZhihuClient()
def client_login(self):
if not os.path.isfile(self.TOKEN_FILE):
self.client.login_in_terminal()
self.client.save_token(self.TOKEN_FILE)
else:
self.client.load_token(self.TOKEN_FILE)
return self.client
def main():
client = ZhihuClient()
try:
client.login('*****@*****.**', 'durant')
except NeedCaptchaException:
print("Login Error")
with open('a.gif', 'wb') as f:
f.write(client.get_captcha())
captcha = input('please input captcha:')
client.login('*****@*****.**', 'durant', captcha)
max_lines = 1
line_saved = 0
data_out_list_a = []
with open(USER_TRY_CSV_PATH) as f:
for line in f.readlines():
craw_id = line.strip("\n")
craw = MyCrawler(craw_id, client)
print(craw_id)
data_a = craw.crawling_answer(craw_id)
if len(data_a) % 60 == 0:
times = int(len(data_a) / 60)
for i in range(times):
data_out_list_a.append(data_a[60 * i:60 * (i + 1)])
else:
print("Invalid Output")
a = random.randint(1, 3)
time.sleep(a)
line_saved += 1
if line_saved == max_lines:
save_to_csv_a(data_out_list_a)
data_out_list_a = []
line_saved = 0
import sys # 修改默认编码
import os # 添加系统路径
import json
base_path = unicode(os.path.abspath('.').decode(sys.stdout.encoding))
sys.path.append(base_path + u'/src/lib')
sys.path.append(base_path + u'/src/lib/oauth')
reload(sys)
sys.setdefaultencoding('utf-8') # 强制使用utf-8编码
from zhihu_oauth import ZhihuClient
from zhihu_oauth.exception import NeedCaptchaException
client = ZhihuClient()
test_email = '*****@*****.**'
test_password = '******'
token_file = './token.pkl'
if os.path.lexists(token_file):
client.load_token(token_file)
print 'load token success'
else:
try:
login_result = client.login(test_email, test_password)
except NeedCaptchaException:
# 保存验证码并提示输入，重新登录
print u'登录失败，需要输入验证码'
with open('a.gif', 'wb') as f:
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('token.pkl')
# replace it as user input
user = client.people('SakuraNekoq')
# Obtain the mapping
print('business', user.business.name)
print('locations', user.locations[0].name)
# -*- coding: utf-8 -*-
import sys
import json
default_encoding = 'utf-8'
if sys.getdefaultencoding() != default_encoding:
reload(sys)
sys.setdefaultencoding(default_encoding)
from zhihu_oauth import ZhihuClient
from neo4j import Database
client = ZhihuClient()
client.load_token('token.pkl')
database = Database()
# me = client.me()
def user_bestanswers():
j = 0
while True:
answerIDs = database.graph.data(
"match(u:User)-[:AUTHOR]->(a:Answer) where a.answer_topic_corresponded is null return a.answerId as answerId skip 800 limit 100"
)
for answerID in answerIDs:
try:
# flag = is_coresspoded(answerID)
# if flag is 1:
# print("抓过了"+str(answerID))
# continue
# coding=utf-8
from __future__ import unicode_literals, print_function
import os
from zhihu_oauth import ZhihuClient
TOKEN_FILE = 'ZHIHUTOKEN.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ========================我========================
me = client.me()
# print('活动', me.activities)
# print('答案数', me.answer_count)
# print('答案', me.answers)
# print('文章', me.articles)
# print('文章数', me.articles_count)
# print('头像地址', me.avatar_url)
# print('用户所在行业', me.business)
# print('收藏数', me.collected_count)
# print('收藏夹数', me.collection_count)
# print('收藏夹', me.collections)
# print('专栏数', me.column_count)
# print('专栏', me.columns)
# print('专栏数', me.columns_count)
# created_at = time.localtime(me.created_at)
# print('创建时间', time.strftime("%Y-%m-%d %H:%M:%S", created_at))
# print('个人描述', me.description)
# print('草稿数', me.draft_count)
# print('教育信息', me.educations)
class Crawler:
client_ = ZhihuClient()
topic_question_df = pd.DataFrame()
topics_list_ = [19610354, 20010203] #监控的话题列表
questions_detail_ = {} #每个问题的问题标题，问题内容，关注人数，回答人数，回答内容，评论内容，包含话题
answers_persisted = set()
answers_to_download = []
def __init__(self, topics_list=[]):
if (len(topics_list) > 0):
self.topic_lists_ = topics_list
if os.path.isfile(TOKEN_FILE):
self.client_.load_token(TOKEN_FILE)
else:
self.client_.login_in_terminal()
self.client_.save_token(TOKEN_FILE)
self.client_.save_token('token.pkl')
self.db_ = MongoClient(host="localhost", port=27017)[DB_NAME]
def get_topics_detail(self):
'''
dataframe format
[topic_id, question_id, answer_id_list]
:return:
'''
#old_topics_detail = pd.DataFrame(list(self.db_[TOPICS_COLLECTION].find()))
#print(old_topics_detail)
for topic_id in self.topics_list_:
count = 0
topic = self.client_.topic(topic_id)
for q in topic.unanswered_questions:
if (count > 0):
break
answers = [ans.id for ans in q.answers]
if (len(answers) > 10): #只记录有人回答的问题id，减少储存量
for ans_id in answers:
self.answers_to_download.append(ans_id)
count += 1
print(len(self.answers_to_download))
# new_record = {
# 'tid' : topic_id,
# 'qid' : q.id,
# 'aids' : answers
#
# }
# if(len(old_topics_detail[(old_topics_detail['tid'] == topic_id) & (old_topics_detail['qid'] == q.id)]) > 0):
# self.db_[TOPICS_COLLECTION].update_one({'tid': topic_id, 'qid': q.id}, {'$set': new_record})
# print("update {}".format(new_record))
# else:
# self.db_[TOPICS_COLLECTION].insert_one(new_record)
# print("insert {}".format(new_record))
#TODO-some rest function here
if (random.randint(0, 100) % 10 == 0):
time.sleep(random.randint(1, 3))
print("sleep done")
arr = np.array(self.answers_to_download)
np.save("answers_to_download.npy", arr)
#TODO-find out how to update this list
def get_questions_detail(self): #只搜集符合一定条件的问题详细内容，如关注者/回答数量等超过一定值，但本值不应较大
#如果mongodb中已经存了回答内容，那么也不考虑作者更新回答的情况，因为答案通常较长，IO成本较高
all_answers_id = pd.DataFrame(list(self.db_[TOPICS_COLLECTION].find()))
for answers in all_answers_id['aids']: #提取每个问题对应的所有回答id
for ans_id in answers:
ans = self.client_.answer(ans_id)
ans_content = Cleaner.filter_tags(ans.content)
comment_content = ""
if (ans.comment_count > 0):
for comment in ans.comments:
comment_content += Cleaner.filter_tags(
comment.content) + "@" #用@分割，以后可以选择直接测情绪也可以每句评论分开测
time.sleep(random.randint(1, 4))
print("ans {} done retrival and cleaning".format(ans.id))
ans_detail = {
'aid': ans_id,
'votes': ans.voteup_count,
'content': ans_content,
'comments': comment_content,
'author_follower_num': ans.author.follower_count
}
self.db_[ANSWERS_COLLECTION].insert_one(ans_detail)
#TODO-data cleaning
#TODO-in what format to save these data
def parse_img_src(self, html):
replace_pattern = r'<[img|IMG].*?/>' # img标签的正则式
img_url_pattern = r'.+?src="(\S+)"' # img_url的正则式
replaced_img_url_list = []
img_url_list = []
need_replace_list = re.findall(replace_pattern, html) # 找到所有的img标签
for tag in need_replace_list:
img_url_list.append(re.findall(img_url_pattern,
tag)[0]) # 找到所有的img_url
return img_url_list
def save_img(self, img_url, file_name, file_path='./images/'):
# 保存图片到磁盘文件夹 file_path中，默认为当前脚本运行目录下的 book\img文件夹
try:
if not os.path.exists(file_path):
# os.mkdir(file_path)
os.makedirs(file_path)
# 获得图片后缀
#file_suffix = os.path.splitext(img_url)[1]
# 拼接图片名（包含路径）
filename = '{}{}{}'.format(file_path, os.sep, file_name)
# 下载图片，并保存到文件夹中
img = requests.get(img_url)
with open(filename, "wb") as f:
f.write(img.content)
except IOError as e:
print("error")
except Exception as e:
print("error")
def download_images(self, path):
'''
answers_to_download里回答的images下载存下来
:return:
'''
for ans_id in self.answers_to_download:
answer = self.client_.answer(ans_id)
content = answer.content
img_src_list = self.parse_img_src(content)
print("img src list : {}".format(img_src_list))
for img_url in img_src_list:
self.save_img(img_url, img_url[-10:], "./images")
print("picture {} download complete".format(img_url))
print("answer {} download complete".format(ans_id))
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ============专栏模块============
cid = 10000
column = client.column(cid)
print('文章数', column.article_count)
print('文章', column.articles)
print('文章数', column.articles_count)
print('作者', column.author)
print('能否评论', column.comment_permission)
print('描述', column.description)
print('关注人数', column.follower_count)
print('关注人', column.followers)
print('问题ID', column.id)
print('图像地址', column.image_url)
print('标题', column.title)
print('是否更新过', column.updated)
print('更新时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(column.updated_time)))
# ================运行时间计时================
run_time = time.time() - start_time
if run_time < 60: # 两位小数的秒
# coding=utf-8
from __future__ import unicode_literals, print_function
import os
from zhihu_oauth import ZhihuClient
TOKEN_FILE = 'token.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login('*****@*****.**', 'Zhihu2Ebook')
client.save_token(TOKEN_FILE)
path_prefix = '/Users/alicewish/我的坚果云/' # 文件地址前缀
txt_file_path = path_prefix + file_name + '.txt' # TXT文件名
# ================按行读取文本================
text_readline = [] # 初始化按行存储数据列表,不接受结尾换行符
with open(txt_file_path) as fin:
for line in fin:
text_readline.append((line).replace('\n', ''))
print(text_readline)
for i in range(len(text_readline)):
print(text_readline[i])
# ================读取账号和密码================
account = text_readline[0]
passward = text_readline[1]
client = ZhihuClient()
try:
client.login(account, passward)
except NeedCaptchaException:
# 保存验证码并提示输入，重新登录
with open('a.gif', 'wb') as f:
f.write(client.get_captcha())
captcha = input('please input captcha:')
client.login(account, passward, captcha)
# 必须在 client 已经处于登录状态时才能使用
client.save_token('/Users/alicewish/我的坚果云/token.pkl')
# ================运行时间计时================
run_time = time.time() - start_time
from __future__ import unicode_literals, print_function
import os
import re
import time
from zhihu_oauth import ZhihuClient
from zhihu_oauth import Topic
from zhihu_oauth import exception
TOKEN_FILE = 'token.cache'
TOP_SIZE = 50
# Login
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
# The topest root of topic
root_topic = client.topic(19776749)
# The array to store top hot topic
hot_topics = list()
# Whether the hot_topics is full
hot_topics_full = False
# The fewest topic in hot_topics
last_topic = {}
return os.listdir()
def get_answers():
return os.listdir(collection_id)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("--collection", "-c", help="Set collection ID, e.g. 99549491")
parser.add_argument("--thread", "-t", help="(Optional) Set the threads, 3 to 7 is recommended, default value is 5.")
parser.add_argument("--upload", "-u", action='store_true', help="Upload the answers to Zhihu.")
parser.add_argument("--download", "-d", action='store_true', help="Download the answers from Zhihu.")
global client
client = ZhihuClient()
client.login_in_terminal()
me = client.me()
args = parser.parse_args()
if args.collection:
print("Selected collection: ", str(args.collection))
collection = client.collection(int(args.collection))
global collection_id
collection_id = str(collection.id)
else:
print("YOU MUST TELL ME WHICH COLLECTION YOU WANT TO ADD IN!!")
exit()
if args.thread:
def login(username, password):
client = ZhihuClient()
client.login_in_terminal(username, password)
return client
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ========================查询问题========================
qid = 48217184
question = client.question(qid)
print('允许删除', question.allow_delete)
print('答案数', question.answer_count)
print('答案', question.answers)
print('评论数', question.comment_count)
print('评论', question.comments)
print('细节', question.detail)
print('摘录', question.excerpt)
print('关注数', question.follower_count)
print('关注人', question.followers)
print('问题ID', question.id)
print('重定向', question.redirection)
print('状态', question.status)
print('建议修改', question.suggest_edit)
print('标题', question.title)
print('话题', question.topics)
print('更新时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(question.updated_time)))
# Create in 2019-05-29
# Project: Store data from Zhihu in Mysql Database
# Author: SHIELD_QIQI
from zhihu_oauth import ZhihuClient
from zhihu_oauth.exception import NeedCaptchaException
from Database import MysqlQI
import jieba
import jieba.analyse
import re
from collections import Counter
import wordcloud
client = ZhihuClient()
# 直接用首次登陆的token文件登陆我的知乎
client.load_token('token.pkl')
# 在数据库中添加删除表为存储数据做准备
mysql = MysqlQI()
# # 删除数据库(urldata)中的所有的表
# tableNum = mysql.cur.execute("SELECT concat('DROP TABLE IF EXISTS ', table_name, ';') ""FROM information_schema.tables WHERE table_schema = 'urldata';")
# print("-------------------------------------\n数据库中原有"+str(tableNum)+"个表")
# print("正在删除.....")
# for i in range(0,tableNum):
# mysql.cur.execute("SELECT concat('DROP TABLE IF EXISTS ', table_name, ';') ""FROM information_schema.tables WHERE table_schema = 'urldata';")
# mysql.cur.execute(mysql.cur.fetchone()[0])
#
# tableNum = mysql.cur.execute("SELECT concat('DROP TABLE IF EXISTS ', table_name, ';') ""FROM information_schema.tables WHERE table_schema = 'urldata';")
# if tableNum == 0:
# print("该数据库下所有表删除完毕\n---------------------------------------")
# else:
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ============文章模块============
aid = 10000
article = client.article(aid)
print('作者', article.author)
print('能否评论', article.can_comment)
print('从属专栏', article.column)
print('评论数', article.comment_count)
print('评论权限', article.comment_permission)
print('评论', article.comments)
print('内容', article.content)
print('摘录', article.excerpt)
print('文章ID', article.id)
print('图像地址', article.image_url)
print('建议修改', article.suggest_edit)
print('标题', article.title)
print('更新时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(article.updated_time)))
print('赞同数', article.voteup_count)
# ================运行时间计时================
run_time = time.time() - start_time
__author__ = 'ipreacher' import time import numpy as np from zhihu_oauth import ZhihuClient from zhihu_oauth.exception import NeedCaptchaException client = ZhihuClient() client.login_in_terminal() me = client.me() t = '你好，感谢关注！\n新的一年里，祝学业进步，工作顺利！\n[This is sent by a robot.]\nipreacher' for f in me.followers: print(f.name) me.message(f, t) time.sleep(10 * abs(np.random.randn()))
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ========================查询答案========================
aid = 34404209
answer = client.answer(aid)
print('作者', answer.author)
print('能否评论', answer.can_comment)
print('收藏夹', answer.collections)
print('评论数', answer.comment_count)
print('评论权限', answer.comment_permission)
print('评论', answer.comments)
print('内容', answer.content)
print('创建时间', answer.created_time)
print('摘录', answer.excerpt)
print('答案ID', answer.id)
print('能否复制', answer.is_copyable)
print('是我回答的吗', answer.is_mine)
print('从属问题', answer.question)
print('建议修改', answer.suggest_edit)
print('感谢数', answer.thanks_count)
print('更新时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(answer.updated_time)))
print('投票者', answer.voters)
# coding=utf-8
# 通过昵称搜索用户token_url
# 具体数据见Excel文件 zhihu_users_token_url.xlsx
from __future__ import unicode_literals, print_function
import os
from zhihu_oauth import ZhihuClient
TOKEN_FILE = 'token.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
user = []
file = open("C:\\Users\\80693\\Desktop\\User_name.txt")
lines = file.readlines()
file.close()
for line in lines:
line = line.strip().split('\t')
peoples = client.search(line, search_type='PEOPLE')
people_five = [p for _, p in zip(range(5), peoples)]
pp = sorted(peoples, key=lambda x: x.obj.follower_count, reverse=True)
p = pp[0].obj
print(p.name.ljust(14), p.id.ljust(40), p.follower_count)
user.append(p.id)
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
import logging
from logging import StreamHandler
from flask import Flask, jsonify, redirect
from flask_cache import Cache
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('token.pkl')
me = client.me()
cache = Cache(config={'CACHE_TYPE': 'simple'})
app = Flask(__name__)
cache.init_app(app)
file_handler = StreamHandler()
app.logger.setLevel(logging.DEBUG)
app.logger.addHandler(file_handler)
@app.route('/', methods=['GET'])
def index_route():
return jsonify({
'author': 'knarfeh',
'author_url': 'http://www.knarfeh.com',
'people': 'http://zhihu-api.knarfeh.com/people/<people_id>',
from __future__ import unicode_literals, print_function
from RedisQueue import RedisQueue
from zhihu_oauth import ZhihuClient
import datetime
import time
import random
import sys
from timeout import timeout
import os
from utils import print_err
from pymongo import MongoClient
MAX_SLEEP_TIME = 15
Cookies_File = './cookies/cookies%s.json' % sys.argv[1]
global client
client = ZhihuClient()
if os.path.isfile(Cookies_File):
client.load_token(Cookies_File)
else:
client_info = open('./cookies/client_info_list.data').readlines()
client_info = client_info[int(sys.argv[1])].strip().split('\t')
client.login_in_terminal(client_info[0], client_info[1])
client.save_token(Cookies_File)
def get_user_questions(uname):
global client
if uname == '':
return
print(uname)
from pylon import create_logger
log = create_logger(__file__)
log_error = create_logger(__file__ + '.error')
class ZhihuParseError(Exception):
def __init__(self, msg=None, value=None):
self.value = value
self.msg = msg
TOKEN_FILE = 'token.pkl'
client = ZhihuClient()
client.load_token(TOKEN_FILE)
def zhihu_answer_url(answer):
'''貌似答案被删也不报错'''
# log('zhihu_answer_url answer' + str(answer))
if isinstance(answer, int):
answer = client.answer(answer)
return 'https://www.zhihu.com/question/{}/answer/{}'.format(answer.question.id, answer.id)
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ========================我========================
me = client.me()
# print('活动', me.activities)
# print('答案数', me.answer_count)
# print('答案', me.answers)
# print('文章', me.articles)
# print('文章数', me.articles_count)
# print('头像地址', me.avatar_url)
# print('用户所在行业', me.business)
# print('收藏数', me.collected_count)
# print('收藏夹数', me.collection_count)
# print('收藏夹', me.collections)
# print('专栏数', me.column_count)
# print('专栏', me.columns)
# print('专栏数', me.columns_count)
# created_at = time.localtime(me.created_at)
# print('创建时间', time.strftime("%Y-%m-%d %H:%M:%S", created_at))
# print('个人描述', me.description)
# print('草稿数', me.draft_count)
# print('教育信息', me.educations)
for _,topic in zip(range(30),list) :
name11=topic.name
best=topic.best_answers
for _,answer in zip(range(30),best):
people=answer.author
if people.name!=namen.decode("utf-8"):
people1 = []
for topic in people.badge.topics:
if topic.name.find(toname.decode("utf-8"))!=-1:
people1.append(topic.name)
dicname[people.name]=people1
return dicname
if __name__ == '__main__':
clean('D:/' + u'py程序' + '/answer1')
client = ZhihuClient()
a=get("你好")
a.denglu(client)
me = client.me()
print me.id
# a.findquestion(client)
#
# list_q=a.Analyse_question(a.dic_name,a.qqcount)
#
# a.Analyse_answer(list_q)
# #Anasly_location(dicall1)
# #
# # # 得到词云回答者信息
# # path1 = 'D:/' + u'py程序' + '/answer/people_qb.txt'
# # hello.ciyun1(path1)
# coding=utf-8
# https://pypi.org/project/zhihu-oauth
from __future__ import unicode_literals, print_function
import os
from zhihu_oauth import ZhihuClient
from zhihu_oauth import SearchType
TOKEN_FILE = 'token.pkl'
client = ZhihuClient()
if os.path.isfile(TOKEN_FILE):
client.load_token(TOKEN_FILE)
else:
client.login_in_terminal()
client.save_token(TOKEN_FILE)
me = client.me()
print('name', me.name)
print('headline', me.headline)
print('description', me.description)
print('following topic count', me.following_topic_count)
print('following people count', me.following_topic_count)
print('followers count', me.follower_count)
print('voteup count', me.voteup_count)
from lxml import html
import requests, time, zhihu_oauth
start_time = time.time() # 初始时间戳
# ========================登录========================
from zhihu_oauth import ZhihuClient
client = ZhihuClient()
client.load_token('/Users/alicewish/我的坚果云/token.pkl')
# ============用户模块============
pid = "edna-krabappel"
people = client.people(pid)
print('活动', people.activities)
print('答案数', people.answer_count)
print('答案', people.answers)
print('文章', people.articles)
print('文章数', people.articles_count)
print('头像地址', people.avatar_url)
print('用户所在行业', people.business)
print('收藏数', people.collected_count)
print('收藏夹数', people.collection_count)
print('收藏夹', people.collections)
print('专栏数', people.column_count)
print('专栏', people.columns)
print('专栏数', people.columns_count)
print('创建时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(people.created_at)))
print('个人描述', people.description)
print('草稿数', people.draft_count)