크롤링 디버그 로그 추가
parent
89ea0c783e
commit
f24ff46b09
|
|
@ -1,6 +1,11 @@
|
|||
import asyncio
|
||||
from playwright.async_api import async_playwright
|
||||
from urllib import parse
|
||||
import time
|
||||
from app.utils.logger import get_logger
|
||||
|
||||
# 로거 설정
|
||||
logger = get_logger("pwscraper")
|
||||
|
||||
class NvMapPwScraper():
|
||||
# cls vars
|
||||
|
|
@ -91,25 +96,41 @@ patchedGetter.toString();''')
|
|||
|
||||
async def get_place_id_url(self, selected):
|
||||
count = 0
|
||||
get_place_id_url_start = time.perf_counter()
|
||||
while (count <= 1):
|
||||
title = selected['title'].replace("<b>", "").replace("</b>", "")
|
||||
address = selected.get('roadAddress', selected['address']).replace("<b>", "").replace("</b>", "")
|
||||
encoded_query = parse.quote(f"{address} {title}")
|
||||
url = f"https://map.naver.com/p/search/{encoded_query}"
|
||||
|
||||
wait_first_start = time.perf_counter()
|
||||
|
||||
await self.goto_url(url, wait_until="networkidle",timeout = self._max_retry/2*1000)
|
||||
|
||||
wait_first_time = (time.perf_counter() - wait_first_start) * 1000
|
||||
|
||||
logger.debug(f"[DEBUG] Try {count+1} : Wait for perfect matching : {wait_first_time}ms")
|
||||
|
||||
if "/place/" in self.page.url:
|
||||
return self.page.url
|
||||
|
||||
logger.debug(f"[DEBUG] Try {count+1} : url place id not found, retry for forced collect answer")
|
||||
|
||||
wait_forced_correct_start = time.perf_counter()
|
||||
|
||||
url = self.page.url.replace("?","?isCorrectAnswer=true&")
|
||||
await self.goto_url(url, wait_until="networkidle",timeout = self._max_retry/2*1000)
|
||||
|
||||
wait_forced_correct_time = (time.perf_counter() - wait_forced_correct_start) * 1000
|
||||
|
||||
logger.debug(f"[DEBUG] Try {count+1} : Wait for forced isCorrectAnswer flag : {wait_forced_correct_time}ms")
|
||||
|
||||
if "/place/" in self.page.url:
|
||||
return self.page.url
|
||||
count += 1
|
||||
|
||||
print("Not found url for {selected}")
|
||||
logger.error("[ERROR] Not found url for {selected}")
|
||||
|
||||
return None # 404
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue