def GetContent(self):
#data base
cur = self.connection.cursor()
#db 테이블 만들기
cur.execute("CREATE TABLE "+ self.table_name +" (category, content, content_detail);")
categories = self.GetCategory()
# My_driver = webdriver 객체
my_driver = webdriver.Chrome(self.webdriver_address)
# 웹 자원 로드를 위해 기다리는 시간 설정 - 기본적으로는 다 로드될 때까지 기다려준다
my_driver.implicitly_wait(self.__waiting_time)
# web connect
my_driver.get(self.page_address)
#self.__categories에서 얻은 정보 이용
for category in categories:
my_driver.find_element(By.LINK_TEXT(category)).send_keys(Keys.ENTER)
page_source = my_driver.page_source
my_soup = BeautifulSoup(page_source,self.parser)
contents_source = my_soup.select(self.content_tag)
#콘텐츠 저장 .db file
for content_source in contents_source:
my_driver.find_element(By.LINK_TEXT(content_source.text)).send_keys(Keys.ENTER)
article_page_source = my_driver.page_source
my_soup_for_article = BeautifulSoup(article_page_source,self.parser)
detail_contents_source = my_soup_for_article.select(self.detail_content_tag)
for detail_content_source in detail_contents_source:
cur.execute("INSERT INTO " +self.table_name +" VALUES(?,?,?)", (category, content_source.text,detail_content_source.text))
self.connection.commit()
my_driver.back()
return
def main():
option = webdriver.ChromeOptions()
option.add_argument('--start-maximized')
option.add_argument(
'--user-agent=Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
)
# prefs = {
# 'profile.default_content_setting_values': {
# 'images': 2
# }
# }
# option.add_experimental_option('prefs', prefs) #不加载图片
# option.set_preference('permissions.default.stylesheet', 2) #不加载css
browser = webdriver.Chrome(chrome_options=option)
browser.get('https://www.taobao.com/')
if browser.find_element_by_link_text("亲，请登录"):
browser.find_element_by_link_text("亲，请登录").click()
print("请在60秒内完成扫码")
time.sleep(60)
browser.get('https://cart.taobao.com/cart.htm')
time.sleep(3)
if browser.find_element(By.CSS_SELECTOR, "#J_SelectAll1"):
browser.find_element(By.CSS_SELECTOR, "#J_SelectAll1").click()
while True:
now = datetime.datetime.now()
now_str = now.strftime('%Y-%m-%d %H:%M:%S.%f')
buy_time = datetime.datetime.strptime(buy_time_str,
"%Y-%m-%d %H:%M:%S")
print('current time is :%s' % now_str)
if now > buy_time:
try:
if browser.find_element(By.CSS_SELECTOR, "#J_Go"):
browser.find_element(By.CSS_SELECTOR, "#J_Go").click()
WebDriverWait(browser, 2, poll_frequency=0.5).until(
expected_conditions.visibility_of(
By.LINK_TEXT('提交订单')))
browser.find_element_by_link_text('提交订单').click()
print('OK!')
time.sleep(5)
else:
time.sleep(0.1)
continue
except:
time.sleep(0.1)
continue
time.sleep(0.1)
def getLocator(self, locator):
by = None
key = locator.split(":")
if len(key) == 1:
by = By.ID(locator)
elif len(key) == 2:
key[0] = key[0].lower()
key[1] = key[1].strip()
if key[0] == "id":
by = By.ID(key[1])
if key[0] == "name":
by = By.NAME(key[1])
if key[0] == "xpath":
by = By.XPATH(key[1])
if key[0] == "linktext":
by = By.LINK_TEXT(key[1])
elif key[0] == "particallinktext":
by = By.PARTIAL_LINK_TEXT(key[1])
else:
print("NO LOCATOR MATCHED")
return by
def to_book(self, book):
self.driver.find_element(By.LINK_TEXT(book)).click()
return ProductPage(self.driver)
