class GetInfoFromZhihu:
from tools import Tools
tools = Tools()
driver = tools.init_web_driver()
driver = tools.login(driver=driver)
driver = tools.click_more(driver=driver)
titlelist = driver.find_elements_by_css_selector(
'#zh-profile-activity-page-list > div')
# zh-profile-activity-page-list > div:nth-child(1)
# zh-profile-activity-page-list > div:nth-child(17) > div
# titlelist = driver.find_elements_by_css_selector('#zh-profile-activity-page-list > div:nth-child(1) > div.zm-profile-section-main.zm-profile-section-activity-main.zm-profile-activity-page-item-main')
print titlelist
resultlist = []
for elem in titlelist:
print '++++' + elem.get_attribute('outerHTML').encode(
'utf-8').strip() + "++++++"
elemHTML = elem.get_attribute('outerHTML').encode('utf-8').strip()
# zh-profile-activity-page-list > div:nth-child(5)
actionType = tools.found_action_type(elemHTML=elemHTML)
context = tools.get_context(elem)
result = [actionType, context]
resultlist.append(result)
tools.write_to_file(resultlist)
# print result + '\n\n\n\n\n\n\n'
# source_code = driver.page_source
driver.close()
def OnCyLoginBtnButton(self, event):
if self.cyLoginEmailTxt.GetValue() == "" or self.cyLoginPasswordTxt.GetValue() == "":
dlg = wx.MessageDialog(self, 'Cy 로그인 정보를 입력하세요.', '알림', wx.OK | wx.ICON_ERROR)
try:
result = dlg.ShowModal()
finally:
dlg.Destroy()
return
# 로그인 프로세스
tools.setButtonState(self, self.STATE_NOWLOGING)
self.folderList = tools.login(self)
if self.folderList == False:
dlg = wx.MessageDialog(self, self.mainStatusBar.GetLabel(), '로그인 중 오류가 발생하였습니다.', wx.OK | wx.ICON_ERROR)
try:
result = dlg.ShowModal()
finally:
dlg.Destroy()
tools.setButtonState(self, self.STATE_INIT)
return
elif self.folderList == []:
return
tools.initChkListBox(self)
tools.setButtonState(self, self.STATE_LOGGED)
self.isRunning = False
#----------------- 로그인 성공------------------
self.mainStatusBar.SetLabel("싸이 로그인 성공")
event.Skip()
#!/usr/bin/env python2
import tools
tools.ABS_DATA_PATH = "../"
tools.login("kevin", "")
exit()
tools.get_a_theme(5, "Martinique")
theme = None
tools.get_a_theme(4, "Vayrac")
theme = None
tools.get_a_theme(11, "Mariage")
tools.print_error_report()
#!/usr/bin/env python2
import tools
tools.login("kevin", "", get_xslt=False, parse_and_transform=False, do_static=False)
tools.get_choix(1, "Root", want_static=False, want_background=False, parse_and_transform=False)
tools.get_a_page("Database?action=TRUNK", save=False, parse_and_transform=False)
page = tools.get_a_page("Database?action=IMPORT", save=False, parse_and_transform=False)
correct = "Export OK" in page
print "Correct ? %s" % correct
exit(0 if correct else 1)
def treat(xml, url, name):
if xml.find("*/exception") is not None:
raise Exception (xml.find("*/exception").text)
return False
def fail(e, url, name, response, content):
import pdb;pdb.set_trace()
pass
tools.callback = treat
tools.fail = fail
def compute(action, mode):
tools.get_a_page("Benchmark?action=%s&mode=%s" % (action, mode))
tools.login("kevin", "", save_index=False, get_xslt=False, do_static=False)
tools.get_choix(5, "Martinique", want_static=False, want_background=False)
with open("benchmark.log", "a+") as f:
f.write("------------- x%d\n" % REPEAT)
action = "TAGS"
for mode in ("TAG_USED", "TAG_NUSED", "TAG_ALL", "TAG_NEVER", "TAG_NEVER_EVER", "TAG_GEO"):
time = timeit.Timer((lambda:compute(action, mode))).timeit(REPEAT)/REPEAT
with open("benchmark.log", "a+") as f:
string = "Action: %s, Mode %s, %s" % (action, mode, time)
print string
f.write(string+"\n")
spam_r = spam_info()
# DRIVER CONFIGS AND DECLARATIONS
if platform.system().lower() == 'linux':
options = webdriver.ChromeOptions()
options.add_argument('--user-data-dir=./User_Data')
options.add_argument("--disable-notifications")
driver = webdriver.Chrome('chromedriver', options=options)
wait = WebDriverWait(driver, 40)
if "./User_Data" not in files:
# login_inf = login_info()
login(driver,
wait,
e_co,
By,
username=login_inf['username'],
password=login_inf['password'])
else:
pass
if '.txt' in spam_r['contact']:
with open(spam_r['contact'], 'r') as listo:
data = listo.read()
list_of_contacts = data.split('\n')
print(list_of_contacts)
spam(driver,
wait,
e_co,
By,
count=spam_r['count'],
def main():
cprint('Starting LDS Tools Automator...', 'green', attrs=['bold'])
cprint('\tFetching data from Google Sheets...', 'cyan')
try:
values = data.get_data()
except ValueError:
cprint('Error: no data in spreadsheet!', 'red', attrs=['bold'])
members = data.parse_data(values)
decoded = json.loads(members)
cprint('\tPulling records...', 'cyan')
username = raw_input(colored('\tLDS Username: '******'yellow'))
password = getpass.getpass(colored('\tLDS Password: '******'yellow'))
session = requests.session()
credentials = tools.login(session, username, password)
mrns = []
for member in decoded:
try:
result = records.pull(member, credentials, session)
mrns.append(result)
cprint('\tsuccess!', 'green')
except AssertionError:
result = {'error': 'non-200 response', 'row': member['id']}
cprint('\terror', 'red', attrs=['bold'])
except (ValueError, KeyError, TypeError):
result = {'error': 'unable to parse JSON', 'row': member['id']}
cprint('\terror', 'red', attrs=['bold'])
row = data.build_pulled_row(result)
data.update_row(row, result['row'])
cprint('\tFetching former bishops...', 'cyan')
count = 0
for member in mrns:
try:
result = bishops.fetch(member, credentials, session)
cprint('\tsuccess!', 'green')
count += 1
except AssertionError:
result = {'error': 'non-200 response', 'row': member['row']}
cprint('\terror', 'red', attrs=['bold'])
except (ValueError, KeyError, TypeError):
result = {'error': 'unable to parse JSON', 'row': member['row']}
cprint('\terror', 'red', attrs=['bold'])
row = data.build_bishop_row(result)
data.update_row(row, result['row'])
msg = 'moved %d records' % len(mrns)
cprint(msg, 'green', attrs=['bold'])
msg = 'found %d bishops' % count
cprint(msg, 'green', attrs=['bold'])
for line in file_obj.readlines():
current_page = line
file_obj.close()
search_url = 'https://shopsearch.taobao.com/search?app=shopsearch&commend=all&q=KEY_WORD&search_type=shop&loc=%E4%B8%8A%E6%B5%B7&isb=1'
'''begin'''
#经过浏览器设置
chrome_options = webdriver.ChromeOptions()
# PROXY = "121.43.189.255:84712394"
# chrome_options.add_argument('--proxy-server=%s' % PROXY)
# chrome_options.add_experimental_option("prefs",{"profile.managed_default_content_settings.images":2})
dr = webdriver.Chrome(
executable_path=
"C:\Users\Administrator\Downloads\chromedriver_win32\chromedriver.exe",
chrome_options=chrome_options)
tools.login(dr, user, password)
main_handler = dr.current_window_handle
if current_page == '': #如果不存在则从搜索进入
dr.get(search_url.replace('KEY_WORD', top))
tools.append(PAGE, 'w', dr.current_url) #保存url
else:
dr.get(current_page)
pack = {'class': top}
index = 0
while True:
tools.scrollToEnd(dr) #滚动到网页末尾
time.sleep(1)
shops = dr.find_elements_by_xpath(
'//a[@class="shop-name J_shop_name"]') #获取所有shop的链接url
for shop in shops:
def compute():
tools.login("kevin", "", save_index=False, do_static=DO_STATIC)
tools.get_a_theme(5, "Martinique", want_static=False, want_background=False)
default=1)
args = parser.parse_args()
args.streaming = args.data_portal_type == 'Streaming'
if not args.streaming:
args.cmd_args = {'Master': ["/app/deploy/scripts/rsa_psi/run_psi_data_join_master.sh"],
'Worker': ["/app/deploy/scripts/rsa_psi/run_psi_data_join_worker.sh"]}
if args.rsa_key_pem is not None:
args.psi_extras = [{"name": "RSA_KEY_PEM", "value": args.rsa_key_pem}]
elif args.rsa_key_path is not None:
args.psi_extras = [{"name": "RSA_KEY_PATH", "value": args.rsa_key_path}]
else:
raise Exception('Either RSA_KEY_PEN or RSA_KEY_PATH must be provided when using PSI.')
args.psi_extras.append({"name": "SIGN_RPC_TIMEOUT_MS", "value": "128000"})
args.url = args.url.strip().rstrip('/') + '/api/v' + str(args.api_version)
cookie = login(args)
federation_json, suffix = build_federation_json(args)
federation_id, federation_name = request_and_response(args=args,
url=args.url + '/federations',
json_data=federation_json,
cookies=cookie,
name_suffix=suffix)
raw_data_json, suffix = build_raw_data(args, federation_id, 'template_json/template_raw_data.json')
raw_data_id, raw_data_name = request_and_response(args=args,
url=args.url + '/raw_data',
json_data=raw_data_json,
cookies=cookie,
name_suffix=suffix)
requests.post(url=args.url + '/raw_data/' + str(raw_data_id) + '/submit', cookies=cookie)
def run(self):
like_count = 0
# hashtags_dict_analysis = {'searched_hashtags': {}} #TODO
# Forbidden hashtags
forbidden = tools.load_json(
os.path.join(os.getcwd(), 'forbidden_hashtags.json'))
forbidden = [str(i) for i in forbidden['hashtags']]
driver = webdriver.Chrome()
driver.maximize_window()
driver.implicitly_wait(5)
url = 'https://www.instagram.com/?hl=en'
driver.get(url)
# Access to log in page
driver.find_element_by_xpath(
'//*[@id="react-root"]/section/main/article/div[2]/div[2]/p/a'
).click()
driver.implicitly_wait(5)
# Log in task
log = tools.load_json(os.path.join(os.getcwd(), 'info.json'))
tools.login(driver, log)
driver.implicitly_wait(5)
# Search bar
while True: #loop pour pick le hashtag randomly
like_limit = random.randint(25, self.max_like_per_round)
hashtag = random.choice(log['search'])
# hashtags_dict_analysis['searched_hashtags'][hashtag] = {}
search = driver.find_element_by_css_selector(
'input[placeholder="Search"]') # find Search bar
search.send_keys(hashtag)
driver.implicitly_wait(5)
# Click on first link
driver.find_element_by_xpath(
'//*[@id="react-root"]/section/nav/div[2]/div/div/div[2]/div[2]/div[2]/div/a[1]'
).click()
driver.implicitly_wait(5)
# Click on 'Load More'
try:
driver.execute_script(
"window.scrollTo(0, document.body.scrollHeight);")
driver.find_element_by_link_text('Load more').click()
except NoSuchElementException:
pass
# Click on first photo
first_photo_xpath = '//*[@id="react-root"]/section/main/article/div[2]/div[1]/div[1]/div[1]/a'
first_photo = driver.find_element_by_xpath(first_photo_xpath)
ActionChains(driver).move_to_element(first_photo).perform(
) # remonter vers la 1er image de 'Most recent'
count_row_scroll = 0
# hashtag_count = 1
try:
row = 1
while True: # tant qu'on peut scroll
count_row_scroll += 1
for col in [1, 2, 3]:
col = str(col)
image_i_xpath = '//*[@id="react-root"]/section/main/article/div[2]/div[1]/div[' + str(
row) + ']/div[' + col + ']/a'
image_i = driver.find_element_by_xpath(image_i_xpath)
ActionChains(driver).move_to_element(image_i).perform()
image_i.click()
username_xpath = '/html/body/div[3]/div/div/div[2]/div/article/header/div[2]/div[1]/div/a'
username = driver.find_element_by_xpath(
username_xpath).get_attribute('title')
if 'shop' in username: # TODO A RETRAVAILLER
pass
else:
caption_xpath = '/html/body/div[3]/div/div/div[2]/div/article/div[2]/div[1]/ul/li'
caption = driver.find_element_by_xpath(
caption_xpath).text
# Get hashtags with regex
# hashtags_ = re.findall(r"#(\w+)", caption)
# hashtags_ = list(set(hashtags_))
# any_in = lambda a, b: bool(set(a).intersection(b)) # intersection between 2 lists
# if any_in(forbidden, hashtags_):
# pass
# else:
# hashtags_dict_analysis['searched_hashtags'][hashtag] = hashtags_
# hashtag_count += 1
# Follow, like
try: # a mettre dans le else
if driver.find_element_by_xpath(
"//button[contains(.,'Following')]"):
print(username + 'is already followed')
except NoSuchElementException:
driver.find_element_by_xpath(
"//button[contains(.,'Follow')]").click()
time.sleep(random.uniform(0.2, 0.8))
try:
driver.find_element_by_xpath(
"//span[contains(.,'Like')]").click()
like_count += 1
# hashtag_count += 1
except NoSuchElementException: # if already liked [contains(., 'Unlike)]
pass
finally:
time.sleep(random.uniform(0.2, 0.8))
driver.find_element_by_xpath(
"//button[contains(.,'Close')]").click()
driver.implicitly_wait(5)
# Scroll down
if count_row_scroll == 4: # 1 new load = 4 lignes de charger
driver.execute_script(
"window.scrollTo(0, document.body.scrollHeight);")
time.sleep(random.uniform(0.3, 0.8))
count_row_scroll = 0
row += 1
if like_count == like_limit: # tous les X likes, stop
stop_ = random.uniform(20, 45)
print(time.localtime(), stop_)
time.sleep(60 * stop_)
like_limit = random.randint(25,
self.max_like_per_round)
print('Onto the next : %s' % (time.strftime(
'%d/%m/20%y_%H:%M:%S', time.localtime())))
except NoSuchElementException: # if no more image
pass # look for another hashtag in search bar
if time.localtime()[7] == self.start[7]: #si meme jour
if time.localtime()[3] == self.start[3] + 10:
self.restart()
else:
self.restart()
except: pass
try: os.mkdir(f'{root}/work-folder/data')
except: pass
try: os.mkdir(f'{root}/trash')
except: pass
cmd = [" "]
tools.loadCache()
while len(cmd):
option = cmd.pop(0)
try:
if option=="new" : tools.new(cmd[0])
elif option=="open" : tools.open_dir(cmd[0])
elif option=="vim" : tools.vim(*cmd)
elif option=="view" : tools.view(*cmd)
elif option=="login": tools.login()
elif option=="post" : tools.post(*cmd)
elif option=="clear": tools.copyTemplates()
elif option=="check": tools.check(True, *cmd)
elif option=="run" : tools.check(False, *cmd)
elif option=="save" : tools.saveSolution(*cmd)
elif option=="rm" : tools.removeFile()
elif option=="help" : print(help_string)
except: print(
f"ERR: {sys.exc_info()[0]} {sys.exc_info()[1]} "+
f"line: {sys.exc_info()[2].tb_lineno}")
print("----------------------------------------------------")
tools.saveCache()
cmd = input("command: ").split()
"desc": "",
"desc_format_id": 0,
"dynamic": "",
"interactive": 0,
"no_reprint": 0,
"subtitles": {
"lan": "",
"open": 0
},
"tag": "录播,%s" % uname,
"tid": 174,
"title": uploadName,
"videos": [
{
"desc": "",
"filename": filename,
"title": "P1"
}
]
}
try:
result = video.video_submit(data, verify)
logger.info('上传结果: %s' % (result))
except:
logger.error('%s[RoomID:%s]投稿失败' % (uname, roomID))
return None
if __name__ == '__main__':
uname, roomID, uploadName, filePath= sys.argv[1:5]
upload(uname,roomID,uploadName,filePath,tools.login())
