Commit @f1427a6e80524cb6df4202d8173f6084f91b96ea - yjyoon/구미시-네이버-블로그-스크레퍼

윤영준 2023-12-14

found the workaround for daum

@f1427a6e80524cb6df4202d8173f6084f91b96ea

2b523c8

f1427a6

daum_cafe_scrapper.py

--- daum_cafe_scrapper.py

+++ daum_cafe_scrapper.py


 import pandas as pd
 import os
 import bs4
+import urllib.parse
 import multiprocessing
 from datetime import datetime, timedelta
 from selenium import webdriver

 def get_url(keyword, start_date, end_date, page_num):
     url = (f"https://search.daum.net/search?"
            f"w=fusion&nil_search=btn&DA=PGD"
-           f"&q={keyword}"
+           f"&q={urllib.parse.quote(keyword)}"
            f"&col=cafe&sort=recency"
            f"&sd={start_date.replace('-','')}000000&ed={end_date.replace('-','')}235959"
            f"&period=u&p={page_num}")

 
 
 def scrap_agent(url, keyword, start_date, end_date, page_num):
+    print(f"working on {start_date} to {end_date}")
     # Chrome WebDriver 설치 경로 가져오기
     chrome_path = ChromeDriverManager().install()
     # WebDriver 설정

 
     # infinity_scroll_to_the_bottom(driver)
 
-    try :
-        single_page_search_result = driver.find_elements(By.CSS_SELECTOR, "c-container.hydrated")
-    except :
-        final_page = regex.search(r'<div id=\"noResult\"', driver.page_source)
-        try :
-            print("No more search_result!")
-            return None
-        except :
-            raise "Error! the page has not loaded properly, you must look for connection!"
+    single_page_search_result = driver.find_elements(By.CSS_SELECTOR, "c-container.hydrated")
 
     search_result_plain_html = single_page_search_result[0].get_attribute('innerHTML')
     formatter = bs4.formatter.HTMLFormatter(indent=1)

     delete_cache(driver)
     driver.close()
 
+    if ret["url"] == []:
+        return None
 
     out_df = pd.DataFrame.from_dict(ret)
     base_dir = "daum_cafe"

 
 
 def daum_cafe_scrapper(keyword, start_date, end_date, interval, browser_thread_count=1):
-
+     # daum starts the page_num from 2
     last_page = 502
-    current_page = 2 # daum starts the page_num from 2
     date_ranges = generate_date_range(start_date, end_date, interval)
     print("!!")
     for date_range in date_ranges:
         ret = 0
-        while ret is not None:
+        current_page = 2
+        while ret is not None or current_page > last_page:
             url = get_url(keyword, date_range[0], date_range[1], current_page)
-            ret = scrap_agent(url, date_range[0], date_range[1], interval, current_page)
+            ret = scrap_agent(url, keyword, date_range[0], date_range[1], current_page)
+            print(ret)
             current_page += 1
 
 if __name__ == "__main__":
-    scrap_agent("https://search.daum.net/search?nil_suggest=btn&w=fusion&DA=SBC&q=%EA%B5%AC%EB%AF%B8&sd=20220101000000&ed=20220101235959&period=u&col=cafe&p=2", "dummy", "dummy", "dummy", "dummy")
+    # scrap_agent("https://search.daum.net/search?&p=3&q=%EA%B5%AC%EB%AF%B8+%EC%A7%80%EC%82%B0%EB%8F%99&col=cafe", "dummy", "dummy", "dummy1", "dummy")
     # scrap_agent("https://search.daum.net/search?w=fusion&nil_search=btn&DA=PGD&q=%EA%B5%AC%EB%AF%B8&col=cafe&sort=recency&sd=20221111000000&ed=20221111235959&period=u&p=5",
     #             "구미",
     #             "2020",
     #             "2020")
-    # daum_cafe_scrapper("선산읍", start_date="2022-01-01", end_date="2022-01-02", interval=1, browser_thread_count=1)
+    daum_cafe_scrapper("선산읍", start_date="2023-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
     # daum_cafe_scrapper("고아읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
     # daum_cafe_scrapper("산동읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
     # daum_cafe_scrapper("도개면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)

2b523c8

f1427a6

naver_blog_info_gatherer.py

--- naver_blog_info_gatherer.py

+++ naver_blog_info_gatherer.py

...	...	@@ -1,4 +1,3 @@
1		-import random
2	1	import re
3	2	import regex
4	3	import time
...	...	@@ -97,7 +96,7 @@
97	96	# WebDriver 초기화
98	97	driver = webdriver.Chrome(service=ChromeService(chrome_path), options=options)
99	98	driver.get(url)
100		- time.sleep(1+2*random.random())
	99	+ time.sleep(2)
101	100	single_page_search_result = driver.find_elements(By.CSS_SELECTOR, ".area_list_search")
102	101
103	102	search_result_plain_html = single_page_search_result[0].get_attribute('innerHTML')
...	...	@@ -237,13 +236,4 @@
237	236
238	237	if __name__ == "__main__":
239	238	#TODO start_page_num must be not working as intended
240		- naver_blog_scrapper("구미 송정동", "2023-02-05", "2023-10-31", 100, 50, 1, 12)
241		- naver_blog_scrapper("구미 비산동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
242		- naver_blog_scrapper("도량동", "2023-02-05", "2023-10-31", 100, 50, 1, 12)
243		- naver_blog_scrapper("공단동", "2022-07-21", "2023-10-31", 100, 50, 1, 12)
244		- naver_blog_scrapper("광평동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
245		- naver_blog_scrapper("상모사곡동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
246		- naver_blog_scrapper("임오동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
247		- naver_blog_scrapper("인동동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
248		- naver_blog_scrapper("진미동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
249		- naver_blog_scrapper("양포동", "2022-01-01", "2023-10-31", 100, 50, 1, 12)
	239	+ naver_blog_scrapper("도개면", "2022-10-28", "2023-10-31", 100, 50, 1, 12) (파일 끝에 줄바꿈 문자 없음)

2b523c8

f1427a6

naver_cafe_inifinityscroll_from_searchengine.py

--- naver_cafe_inifinityscroll_from_searchengine.py

+++ naver_cafe_inifinityscroll_from_searchengine.py


 from tqdm import tqdm
 from joblib import Parallel, delayed
 from utils.cache_clear import delete_cache
-from utils.infinity_scroll import infinity_scroll_to_the_bottom
 import warnings
 
 
 def get_url(keyword, start_date, end_date):
     # 오케이독본점 SEO 고용함. 스팸 개쩜
     url = (
-        f"https://search.naver.com/search.naver?where=articleg&query={keyword} -오케이독본점 -부동산 -강아지무료분양&ie=utf8"
-        "&st=date&date_option=8"
-        f"&date_from={start_date.replace('-', '.')}&date_to={end_date.replace('-', '.')}"
-        "&srchby=text"
-        "&dup_remove=1"
-        "&cafe_url=&without_cafe_url="
-        "&sm=tab_opt&nso=so"
-        f"%3Add%2Cp%3Afrom{start_date.replace('-', '')}to{end_date.replace('-', '')}&nso_open=1&prdtype=0"
-   )
+        f"https://search.naver.com/search.naver?"
+        f'nso=so%3Add%2Cp%3Afrom{start_date.replace("-", "")}to{end_date.replace("-", "")}'
+        f'&nso_open=1&prdtype=0&query={keyword}+-오케이독본점'
+        f'&sm=mtb_opt'
+        f'&st=date'
+        f'&stnm=date&where=articleg'
+        f'&opt_tab=0'
+        f'&date_from={start_date.replace("-", "")}&date_to={end_date.replace("-", "")}'
+    )
 
+        # f"https://search.naver.com/search.naver?where=articleg&query={keyword}+-오케이독본점&nso_open=1&prdtype=0"
+        #    f"&oquery={keyword}"
+        #    f"&ie=utf8&st=rel&date_option=8"
+        #    f"&date_from={start_date.replace('-','.')}"
+        #    f"&date_to={end_date.replace('-','.')}"
+        #    f"&srchby=text&dup_remove=1"
+        #    f"&cafe_url=&without_cafe_url="
+        #    f"&sm=tab_opt&nso=so%3Add%2Cp%3Afrom{start_date.replace('-','')}to{end_date.replace('-','')}&nso_open=1&prdtype=0")
     return url
 
 def remove_tags(html):

     # return data by retrieving the tag content
     return ' '.join(soup.stripped_strings)
 
+def infinity_scroll_to_the_bottom(driver):
+    # Automatically scroll the page
+    MAXITER = 2000
+    scroll_pause_time = 0.1 + random.random() * 2  # Pause between each scroll
+    screen_height = driver.execute_script("return window.screen.height;")  # Browser window height
+    i = 1
+    while i < MAXITER:
+        # Scroll down
+        driver.execute_script(f"window.scrollTo(0, {screen_height * i + random.randint(1, 500)});")
+        i += 1
+        time.sleep(scroll_pause_time)
 
+        # Check if reaching the end of the page
+        scroll_height = driver.execute_script("return document.body.scrollHeight;")
+        # print(scroll_height)
+        if screen_height * i > scroll_height:
+            break
+    return driver
 
 def scrap_agent(url, keyword, start_date, end_date):
     # Chrome WebDriver 설치 경로 가져오기

 
     infinity_scroll_to_the_bottom(driver)
 
-
     single_page_search_result = driver.find_elements(By.CSS_SELECTOR, ".lst_view")
-    if single_page_search_result==[] :
-        print("There is no result! really, None, or you can check it by yourself at :\n"
-              f"{url}\n"
-              f"this is with keyword {keyword} with time range {start_date} ~ {end_date}")
-        return None
 
     search_result_plain_html = single_page_search_result[0].get_attribute('innerHTML')
     formatter = bs4.formatter.HTMLFormatter(indent=1)

 
 
 if __name__ == "__main__":
-    # naver_cafe_scrapper("선산읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("고아읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("산동읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("도개면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("장천면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("무을면", start_date="2023-10-23", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("해평면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    # naver_cafe_scrapper("옥성면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
-    naver_cafe_scrapper("구미 송정동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
-    naver_cafe_scrapper("원평동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
-    naver_cafe_scrapper("구미 지산동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
-    naver_cafe_scrapper("도량동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
-    naver_cafe_scrapper("선주원남동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
+    naver_cafe_scrapper("선산읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("고아읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("산동읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("도개면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("장천면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("무을면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("해평면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("옥성면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
+    naver_cafe_scrapper("구미 송정동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
+    naver_cafe_scrapper("원평동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
+    naver_cafe_scrapper("구미 지산동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
+    naver_cafe_scrapper("도량동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
+    naver_cafe_scrapper("선주원남동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
     naver_cafe_scrapper("신평1동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
     naver_cafe_scrapper("신평2동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
     naver_cafe_scrapper("형곡1동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)

Add a comment

Open 0
Closed 0

List

...	...	@@ -4,6 +4,7 @@
4	4	import pandas as pd
5	5	import os
6	6	import bs4
	7	+import urllib.parse
7	8	import multiprocessing
8	9	from datetime import datetime, timedelta
9	10	from selenium import webdriver
...	...	@@ -17,7 +18,7 @@
17	18	def get_url(keyword, start_date, end_date, page_num):
18	19	url = (f"https://search.daum.net/search?"
19	20	f"w=fusion&nil_search=btn&DA=PGD"
20		- f"&q={keyword}"
	21	+ f"&q={urllib.parse.quote(keyword)}"
21	22	f"&col=cafe&sort=recency"
22	23	f"&sd={start_date.replace('-','')}000000&ed={end_date.replace('-','')}235959"
23	24	f"&period=u&p={page_num}")
...	...	@@ -37,6 +38,7 @@
37	38
38	39
39	40	def scrap_agent(url, keyword, start_date, end_date, page_num):
	41	+ print(f"working on {start_date} to {end_date}")
40	42	# Chrome WebDriver 설치 경로 가져오기
41	43	chrome_path = ChromeDriverManager().install()
42	44	# WebDriver 설정
...	...	@@ -55,15 +57,7 @@
55	57
56	58	# infinity_scroll_to_the_bottom(driver)
57	59
58		- try :
59		- single_page_search_result = driver.find_elements(By.CSS_SELECTOR, "c-container.hydrated")
60		- except :
61		- final_page = regex.search(r'<div id=\"noResult\"', driver.page_source)
62		- try :
63		- print("No more search_result!")
64		- return None
65		- except :
66		- raise "Error! the page has not loaded properly, you must look for connection!"
	60	+ single_page_search_result = driver.find_elements(By.CSS_SELECTOR, "c-container.hydrated")
67	61
68	62	search_result_plain_html = single_page_search_result[0].get_attribute('innerHTML')
69	63	formatter = bs4.formatter.HTMLFormatter(indent=1)
...	...	@@ -105,6 +99,8 @@
105	99	delete_cache(driver)
106	100	driver.close()
107	101
	102	+ if ret["url"] == []:
	103	+ return None
108	104
109	105	out_df = pd.DataFrame.from_dict(ret)
110	106	base_dir = "daum_cafe"
...	...	@@ -161,25 +157,26 @@
161	157
162	158
163	159	def daum_cafe_scrapper(keyword, start_date, end_date, interval, browser_thread_count=1):
164		-
	160	+ # daum starts the page_num from 2
165	161	last_page = 502
166		- current_page = 2 # daum starts the page_num from 2
167	162	date_ranges = generate_date_range(start_date, end_date, interval)
168	163	print("!!")
169	164	for date_range in date_ranges:
170	165	ret = 0
171		- while ret is not None:
	166	+ current_page = 2
	167	+ while ret is not None or current_page > last_page:
172	168	url = get_url(keyword, date_range[0], date_range[1], current_page)
173		- ret = scrap_agent(url, date_range[0], date_range[1], interval, current_page)
	169	+ ret = scrap_agent(url, keyword, date_range[0], date_range[1], current_page)
	170	+ print(ret)
174	171	current_page += 1
175	172
176	173	if __name__ == "__main__":
177		- scrap_agent("https://search.daum.net/search?nil_suggest=btn&w=fusion&DA=SBC&q=%EA%B5%AC%EB%AF%B8&sd=20220101000000&ed=20220101235959&period=u&col=cafe&p=2", "dummy", "dummy", "dummy", "dummy")
	174	+ # scrap_agent("https://search.daum.net/search?&p=3&q=%EA%B5%AC%EB%AF%B8+%EC%A7%80%EC%82%B0%EB%8F%99&col=cafe", "dummy", "dummy", "dummy1", "dummy")
178	175	# scrap_agent("https://search.daum.net/search?w=fusion&nil_search=btn&DA=PGD&q=%EA%B5%AC%EB%AF%B8&col=cafe&sort=recency&sd=20221111000000&ed=20221111235959&period=u&p=5",
179	176	# "구미",
180	177	# "2020",
181	178	# "2020")
182		- # daum_cafe_scrapper("선산읍", start_date="2022-01-01", end_date="2022-01-02", interval=1, browser_thread_count=1)
	179	+ daum_cafe_scrapper("선산읍", start_date="2023-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
183	180	# daum_cafe_scrapper("고아읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
184	181	# daum_cafe_scrapper("산동읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
185	182	# daum_cafe_scrapper("도개면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)

...	...	@@ -15,23 +15,30 @@
15	15	from tqdm import tqdm
16	16	from joblib import Parallel, delayed
17	17	from utils.cache_clear import delete_cache
18		-from utils.infinity_scroll import infinity_scroll_to_the_bottom
19	18	import warnings
20	19
21	20
22	21	def get_url(keyword, start_date, end_date):
23	22	# 오케이독본점 SEO 고용함. 스팸 개쩜
24	23	url = (
25		- f"https://search.naver.com/search.naver?where=articleg&query={keyword} -오케이독본점 -부동산 -강아지무료분양&ie=utf8"
26		- "&st=date&date_option=8"
27		- f"&date_from={start_date.replace('-', '.')}&date_to={end_date.replace('-', '.')}"
28		- "&srchby=text"
29		- "&dup_remove=1"
30		- "&cafe_url=&without_cafe_url="
31		- "&sm=tab_opt&nso=so"
32		- f"%3Add%2Cp%3Afrom{start_date.replace('-', '')}to{end_date.replace('-', '')}&nso_open=1&prdtype=0"
33		- )
	24	+ f"https://search.naver.com/search.naver?"
	25	+ f'nso=so%3Add%2Cp%3Afrom{start_date.replace("-", "")}to{end_date.replace("-", "")}'
	26	+ f'&nso_open=1&prdtype=0&query={keyword}+-오케이독본점'
	27	+ f'&sm=mtb_opt'
	28	+ f'&st=date'
	29	+ f'&stnm=date&where=articleg'
	30	+ f'&opt_tab=0'
	31	+ f'&date_from={start_date.replace("-", "")}&date_to={end_date.replace("-", "")}'
	32	+ )
34	33
	34	+ # f"https://search.naver.com/search.naver?where=articleg&query={keyword}+-오케이독본점&nso_open=1&prdtype=0"
	35	+ # f"&oquery={keyword}"
	36	+ # f"&ie=utf8&st=rel&date_option=8"
	37	+ # f"&date_from={start_date.replace('-','.')}"
	38	+ # f"&date_to={end_date.replace('-','.')}"
	39	+ # f"&srchby=text&dup_remove=1"
	40	+ # f"&cafe_url=&without_cafe_url="
	41	+ # f"&sm=tab_opt&nso=so%3Add%2Cp%3Afrom{start_date.replace('-','')}to{end_date.replace('-','')}&nso_open=1&prdtype=0")
35	42	return url
36	43
37	44	def remove_tags(html):
...	...	@@ -45,7 +52,24 @@
45	52	# return data by retrieving the tag content
46	53	return ' '.join(soup.stripped_strings)
47	54
	55	+def infinity_scroll_to_the_bottom(driver):
	56	+ # Automatically scroll the page
	57	+ MAXITER = 2000
	58	+ scroll_pause_time = 0.1 + random.random() * 2 # Pause between each scroll
	59	+ screen_height = driver.execute_script("return window.screen.height;") # Browser window height
	60	+ i = 1
	61	+ while i < MAXITER:
	62	+ # Scroll down
	63	+ driver.execute_script(f"window.scrollTo(0, {screen_height * i + random.randint(1, 500)});")
	64	+ i += 1
	65	+ time.sleep(scroll_pause_time)
48	66
	67	+ # Check if reaching the end of the page
	68	+ scroll_height = driver.execute_script("return document.body.scrollHeight;")
	69	+ # print(scroll_height)
	70	+ if screen_height * i > scroll_height:
	71	+ break
	72	+ return driver
49	73
50	74	def scrap_agent(url, keyword, start_date, end_date):
51	75	# Chrome WebDriver 설치 경로 가져오기
...	...	@@ -66,13 +90,7 @@
66	90
67	91	infinity_scroll_to_the_bottom(driver)
68	92
69		-
70	93	single_page_search_result = driver.find_elements(By.CSS_SELECTOR, ".lst_view")
71		- if single_page_search_result==[] :
72		- print("There is no result! really, None, or you can check it by yourself at :\n"
73		- f"{url}\n"
74		- f"this is with keyword {keyword} with time range {start_date} ~ {end_date}")
75		- return None
76	94
77	95	search_result_plain_html = single_page_search_result[0].get_attribute('innerHTML')
78	96	formatter = bs4.formatter.HTMLFormatter(indent=1)
...	...	@@ -175,19 +193,19 @@
175	193
176	194
177	195	if __name__ == "__main__":
178		- # naver_cafe_scrapper("선산읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
179		- # naver_cafe_scrapper("고아읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
180		- # naver_cafe_scrapper("산동읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
181		- # naver_cafe_scrapper("도개면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
182		- # naver_cafe_scrapper("장천면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
183		- # naver_cafe_scrapper("무을면", start_date="2023-10-23", end_date="2023-10-31", interval=30, browser_thread_count=1)
184		- # naver_cafe_scrapper("해평면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
185		- # naver_cafe_scrapper("옥성면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
186		- naver_cafe_scrapper("구미 송정동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
187		- naver_cafe_scrapper("원평동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
188		- naver_cafe_scrapper("구미 지산동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
189		- naver_cafe_scrapper("도량동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
190		- naver_cafe_scrapper("선주원남동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=2)
	196	+ naver_cafe_scrapper("선산읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	197	+ naver_cafe_scrapper("고아읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	198	+ naver_cafe_scrapper("산동읍", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	199	+ naver_cafe_scrapper("도개면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	200	+ naver_cafe_scrapper("장천면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	201	+ naver_cafe_scrapper("무을면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	202	+ naver_cafe_scrapper("해평면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	203	+ naver_cafe_scrapper("옥성면", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
	204	+ naver_cafe_scrapper("구미 송정동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
	205	+ naver_cafe_scrapper("원평동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
	206	+ naver_cafe_scrapper("구미 지산동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
	207	+ naver_cafe_scrapper("도량동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
	208	+ naver_cafe_scrapper("선주원남동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
191	209	naver_cafe_scrapper("신평1동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
192	210	naver_cafe_scrapper("신평2동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
193	211	naver_cafe_scrapper("형곡1동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)

Delete comment