File name
Commit message
Commit date
2023-12-12
2023-12-13
2023-12-13
2023-12-13
import random
import re
import regex
import time
import math
import pandas as pd
import os
import bs4
from bs4 import MarkupResemblesLocatorWarning
from datetime import datetime, timedelta
from selenium import webdriver
from selenium.webdriver.common.by import By
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.service import Service as ChromeService
from tqdm import tqdm
from joblib import Parallel, delayed
from utils.cache_clear import delete_cache
import warnings
def get_url(keyword, start_date, end_date):
url = (f"https://search.naver.com/search.naver?where=articleg&query={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):
# parse html content
soup = bs4.BeautifulSoup(html, "html.parser")
for data in soup(['style', 'script']):
# Remove tags
data.decompose()
# 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
chrome_path = ChromeDriverManager().install()
# WebDriver 설정
options = webdriver.ChromeOptions()
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option("useAutomationExtension", False)
options.add_argument('headless')
options.add_argument('window-size=1920x1080')
options.add_argument("disable-gpu")
# options.add_argument("user-agent=Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko")
# WebDriver 초기화
driver = webdriver.Chrome(service=ChromeService(chrome_path), options=options)
driver.get(url)
time.sleep(2)
infinity_scroll_to_the_bottom(driver)
single_page_search_result = driver.find_elements(By.CSS_SELECTOR, ".lst_view")
search_result_plain_html = single_page_search_result[0].get_attribute('innerHTML')
formatter = bs4.formatter.HTMLFormatter(indent=1)
search_result_plain_html_beautified = bs4.BeautifulSoup(search_result_plain_html, 'html.parser').prettify(formatter=formatter)
search_result_contents = regex.findall(r'<li class="bx">(.*?)\n<\/li>', search_result_plain_html_beautified, re.DOTALL)
ret = {
"url": [],
"title": [],
"cafe_name": [],
"post_date": [],
"text": []
}
for content in search_result_contents:
content = content.replace("\n", "")
href = "/".join(str(i) for i in regex.findall(r'href="([^"]+)/([^"]+)/([^"]+)/([^"]+)"', content, re.DOTALL)[0])
title = regex.search(r'<div class="title_area">(.*?) </div>',content)
text = regex.search(r' <div class="dsc_area">(.*?) <\/div>',content)
cafe_name = regex.search(r' <div class="user_info">(.*?) </div>',content)
post_date = regex.search(r'<span class="sub">(.*?)<\/span>',content)
title = remove_tags(title.group(1))
title = title[:-11] # to remove date
text = remove_tags(text.group(1))
cafe_name = remove_tags(cafe_name.group(1))
post_date = remove_tags((post_date.group(1)))
ret["url"].append(href)
ret["title"].append(title)
ret["cafe_name"].append(cafe_name)
ret["post_date"].append(post_date)
ret["text"].append(text)
delete_cache(driver)
driver.close()
# merged_result = merge_dicts(ret)
out_df = pd.DataFrame.from_dict(ret)
if not os.path.exists(f"cafe/{keyword}"):
os.mkdir(f"cafe/{keyword}")
out_df.to_csv(f"cafe/{keyword}/{start_date}-{end_date}.csv", index=False)
return ret
def merge_dicts(dict_list):
# Initialize the result dictionary with empty lists
result = {
"url": [],
"title": [],
"blog_name": [],
"post_date": [],
"text": []
}
# Iterate through each dictionary and merge the lists
for d in dict_list:
for key in result.keys():
result[key].extend(d.get(key, []))
return result
def generate_date_range(start_date, end_date, interval):
"""
:param start_date: start date in datetimestr formatted in %Y-%m-%d
:param end_date: end date in datetimestr formatted in %Y-%m-%d
:param interval: interval of time in DAYS
:return: returns list of time interval that will be feeded into naver_blog_scrapper.
for example, [[2023-10-01, 2023-10-07],[2023-10-08, 2023-10-14]] for generate_date_range("2023-10-01", "2023-10-14", 7)
Also, this function can handle when the time range of start and end date is not perfectly divisible by interval
generate_date_range("2023-10-01", "2023-10-14", 10) will produce output [['2023-10-01', '2023-10-10'], ['2023-10-11', '2023-10-14']]
"""
# Convert the start and end date strings to datetime objects
start = datetime.strptime(start_date, "%Y-%m-%d")
end = datetime.strptime(end_date, "%Y-%m-%d")
# Generate a range of dates from start to end
date_ranges = []
current_date = start
while current_date < end:
current_end = min(current_date + timedelta(days=interval - 1), end)
date_ranges.append([current_date.strftime("%Y-%m-%d"), current_end.strftime("%Y-%m-%d")])
current_date = current_end + timedelta(days=1)
return date_ranges
def naver_cafe_scrapper(keyword, start_date, end_date, interval, browser_thread_count=1):
date_ranges = generate_date_range(start_date, end_date, interval)
urls = []
for date_range in date_ranges:
urls.append(get_url(keyword, date_range[0], date_range[1]))
pass
def parallel_scraping(keyword):
results = Parallel(n_jobs=browser_thread_count)(delayed(scrap_agent)(url, keyword, date_ranges[i][0], date_ranges[i][1]) for i, url in enumerate(urls))
return results
ret = parallel_scraping(keyword)
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="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)
naver_cafe_scrapper("형곡2동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("구미 비산동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("공단동", start_date="2022-01-01", end_date="2023-10-31", interval=10, browser_thread_count=1)
naver_cafe_scrapper("광평동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("상모사곡동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("임오동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("인동동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("진미동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("양표동", start_date="2022-01-01", end_date="2023-10-31", interval=30, browser_thread_count=1)
naver_cafe_scrapper("구미", start_date="2022-01-01", end_date="2023-10-31", interval=1, browser_thread_count=1)
naver_cafe_scrapper("구미시장", start_date="2022-01-01", end_date="2023-10-31", interval=7, browser_thread_count=1)