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
def login(account, password):
client = ZhihuClient()
try:
client.load_token(TOKEN_FILE)
except FileNotFoundError:
try:
client.login(account, password)
except NeedCaptchaException:
# 保存验证码并提示输入，重新登录
with open('./captcha/a.gif', 'wb') as f:
f.write(client.get_captcha())
captcha = input('please input captcha:')
client.login(account, password, captcha)
client.save_token('./token/token.pkl')
finally:
return client
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 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
from zhihu_oauth import ZhihuClient
from zhihu_oauth.exception import NeedCaptchaException
#custom your email/phone number matched with password
email = ""
password = ""
client = ZhihuClient()
try:
client.login(email, 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, password, captcha)
client.save_token('token.pkl')
class Crawl:
def __init__(self):
self.client = ZhihuClient()
def login(self, username, password):
if os.path.isfile('app/Resource/' + username + '.token'):
self.client.load_token('app/Resource/' + username + '.token')
else:
try:
self.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(self.client.get_captcha())
captcha = input('please input captcha:')
self.client.login(username, password, captcha)
self.client.save_token('app/Resource/' + username + '.token')
def get_live_list(self):
lives = self.client.me().lives
return lives
@staticmethod
def save_live_list(livedata):
new_live = MyLive(live_id=livedata.id,
title=livedata.title,
speaker=livedata.speaker.name,
speaker_description=livedata.speaker.description,
live_description=livedata.description,
seats_count=livedata.seat_taken,
price=livedata.fee)
new_live.save()
def live_list_work(self):
for live in self.get_live_list():
exist = MyLive.objects(live_id=live.id)
if not exist:
self.save_live_list(live)
def get_live_content(self, live_id, before_id=''):
res = self.client._session.get(
LIVECONTENT_URL.format(live_id, before_id))
data = json.loads(res.content)
return data
def save_live_content_image(self, id, url):
content = self.client._session.get(url).content
file = 'app/Resource/' + str(id) + '.png'
with open(file, 'wb') as f:
f.write(content)
@staticmethod
def save_live_content(live_id, livedata):
for r in livedata['data']:
exist = LiveContent.objects(message_id=r['id'])
if exist:
continue
if r['type'] == 'audio':
url = r['audio']['url']
elif r['type'] == 'image':
url = r['image']['full']['url']
else:
url = ''
content = r['text'] if 'text' in r else ''
reply = ','.join(r['replies']) if 'replies' in r else ''
new_live_content = LiveContent(
message_id=int(r['id']),
sender=r['sender']['member']['name'],
type=r['type'],
content=content,
url=url,
reply=reply,
likes=r['likes']['count'],
created_at=datetime.fromtimestamp((r['created_at'])),
live_title=live_id)
new_live_content.save()
def live_content_work(self, id):
live = MyLive.objects(id=id).first()
# 使用知乎的live的ID值传入获取详情
data = self.get_live_content(live.live_id)
while data['unload_count'] > 0:
# 存储时使用mongo的ID值传入
self.save_live_content(live.id, data)
data = self.get_live_content(live.live_id, data['data'][0]['id'])
else:
print('success')
image_contents = LiveContent.objects(live_title=live.id, type='image')
for item in image_contents:
self.save_live_content_image(item.id, item.url)
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:
f.write(client.get_captcha())
captcha = raw_input(u'please input captcha:')
login_result = client.login(test_email, test_password, captcha)
print 'login result => '
print login_result
client.save_token(token_file)
print 'save token success'
# question
response_file_uri = './question_response.html' # 将json输出到网页中，chrome下按F12选preview能看见浏览器渲染出的json数据结构
question_id = 35005800
question = client.question(question_id)
data = question.pure_data
response_json = json.dumps(data)
response_file = open(response_file_uri, 'w+')
response_file.write(response_json)