def __init__(self, key, url, search):
## regexp
self.__blog_target_reg = re.compile('blog.naver.com')
self.__palce_target_reg = re.compile('store.naver.com/restaurants/detail')
self.__log_reg = re.compile('(?<=logNo=)\w+')
self.__basic_reg = re.compile('^[^?]+')
self.__dir_reg = re.compile('(?<=dirId=)\w+')
self.__doc_reg = re.compile('(?<=docId=)\w+')
self.__id_reg = re.compile("(?<=id=)\w+")
self.__key = key
self.__search_type = search
self.__where = self.search_type(self.__search_type)
self.__url = self.format_kin_url(url) if self.__search_type == "kin" else common.deleteHttp(url)
## naver place 외 default url 적용
self.__default_url = "https://search.naver.com/search.naver?where={0}&query={1}".format(self.__where, self.__key)
self.__place_url = "https://store.naver.com/restaurants/list?query={0}".format(self.__key)
self.__driver_url = self.__place_url if self.__search_type == "place" else self.__default_url
## chrome driver
self.driver = webdriver.Chrome("./chromedriver")
self.driver.implicitly_wait(1)
self.__post_rank = None
def format_blog_url(self, url):
check_url = common.deleteHttp(url)
reg_url = self.__blog_target_reg.search(check_url)
if reg_url is not None:
log_no = self.__log_reg.search(check_url).group()
basic_url = self.__basic_reg.search(check_url).group()
check_url = "{0}/{1}".format(basic_url, log_no)
return check_url
def check_post_rank(self, li_list):
post_rank = False
for idx, val in enumerate(li_list, 1):
link = val.find('a', class_=self.__a_link_class).get("href")
check_url = common.deleteHttp(link)
if check_url == self.__url:
post_rank = idx
break
return post_rank
def format_kin_url(self, url):
try:
check_url = common.deleteHttp(url)
reg_url = self.__basic_reg.search(check_url).group()
if reg_url is not None:
dirId = self.__dir_reg.search(check_url).group()
docId = self.__doc_reg.search(check_url).group()
check_url = "{0}?dirId={1}&docId={2}".format(reg_url, dirId, docId)
except AttributeError:
return -1
else:
return check_url
def find_target_post(self):
post_rank = None
## url
current = self.driver.current_url
## page parameter url
start_str = self.make_start_str(self.__search_type)
## element selector
a_link_class = self.make_a_link_class(self.__search_type)
list_container = self.make_list_container(self.__search_type)
list_item = "{0} > {1}".format(self.make_ul_select(self.__search_type), self.make_li_select(self.__search_type))
## naver 탐색
for x in range(0, 10):
pages = (x + 1) if self.__search_type == 'place' else (x * 10) + 1
current_page = start_str + repr(pages)
self.driver.get(current + current_page)
## naver list container element 가져오기
html = self.driver.find_element_by_css_selector(list_container).get_attribute('innerHTML')
## HTML Parsing
soup = BeautifulSoup(html, 'html.parser')
li_list = soup.select(list_item)
isBreak = False
for idx, val in enumerate(li_list, 1):
a_tag = val.find('a', class_= a_link_class)
link = str()
if a_tag is not None:
link = a_tag.get('href')
check_url = str()
if self.__search_type == 'blog':
check_url = self.format_blog_url(link)
elif self.__search_type == 'kin':
check_url = self.format_kin_url(link)
elif self.__search_type == 'place':
check_url = self.format_place_url(link)
else:
check_url = common.deleteHttp(link)
if check_url == self.__url:
isBreak = True
post_rank = (x * 10 + idx)
break
if isBreak:
return post_rank
def __init__(self, key, url, sort_type):
self.__key = key
self.__sort_type = sort_type
self.__url = common.deleteHttp(url)
self.__driver_url = "https://map.kakao.com/?from=total&q={0}&tab=place&nil_suggest=btn".format(
self.__key)
## element css selector
self.__list_container = ".placelist"
self.__li_select = ".PlaceItem"
self.__a_link_class = "moreview"
## rank
self.__post_rank = None
## chrome driver
self.driver = webdriver.Chrome("./chromedriver")
self.driver.implicitly_wait(1)
self.num_of_page = 2
def format_place_url(self, url):
check_url = common.deleteHttp(url)
basic_url = self.__basic_reg.search(check_url).group()
url_id = self.__id_reg.search(check_url).group()
check_url = "{0}?id={1}".format(basic_url, url_id)
return check_url