当我在列表中搜索多个关键字时，脚本不起作用
Script doesn't work when I go for multiple search keywords in the list
我创建了一个脚本，当我使用不同的关键字开始搜索时，从 search engine 中获取不同的报纸名称，如 CMG제약、DB하이텍 e.t.c .在该页面右上角的搜索框中。
我还在参数中使用了一些自定义日期来获取这些日期的结果。只要我在搜索列表中使用 单个关键字 ，脚本就可以正常运行。
但是，当我在搜索列表中使用多个关键字时，脚本只会跟上最后一个关键字。这是我想使用的关键字列表：
keywords = ['CMG제약','DB하이텍','ES큐브','EV첨단소재']
脚本比较短但是因为参数的高度，看起来比较大
到目前为止我已经尝试过 (works as intended as I used single search keyword in the list):
import requests
import concurrent.futures
from bs4 import BeautifulSoup
from urllib.parse import urljoin
year_list_start = ['2013.01.01','2014.01.02']
year_list_upto = ['2014.01.01','2015.01.01']
base = 'https://search.naver.com/search.naver'
link = 'https://search.naver.com/search.naver'
params = {
'where': 'news',
'sm': 'tab_pge',
'query': '',
'sort': '1',
'photo': '0',
'field': '0',
'pd': '',
'ds': '',
'de': '',
'cluster_rank': '',
'mynews': '0',
'office_type': '0',
'office_section_code': '0',
'news_office_checked': '',
'nso': '',
'start': '',
}
def fetch_content(s,keyword,link,params):
for start_date,date_upto in zip(year_list_start,year_list_upto):
ds = start_date.replace(".","")
de = date_upto.replace(".","")
params['query'] = keyword
params['ds'] = ds
params['de'] = de
params['nso'] = f'so:r,p:from{ds}to{de},a:all'
params['start'] = 1
while True:
res = s.get(link,params=params)
print(res.status_code)
print(res.url)
soup = BeautifulSoup(res.text,"lxml")
if not soup.select_one("ul.list_news .news_area .info_group > a.press"): break
for item in soup.select("ul.list_news .news_area"):
newspaper_name = item.select_one(".info_group > a.press").get_text(strip=True).lstrip("=")
print(newspaper_name)
if soup.select_one("a.btn_next[aria-disabled='true']"): break
next_page = soup.select_one("a.btn_next").get("href")
link = urljoin(base,next_page)
params = None
if __name__ == '__main__':
with requests.Session() as s:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36'
keywords = ['CMG제약']
with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
future_to_url = {executor.submit(fetch_content, s, keyword, link, params): keyword for keyword in keywords}
concurrent.futures.as_completed(future_to_url)
How can I make the script work when there are more than one keyword in the search list?
我认为问题在于变量 params 过早地被后续请求的数据覆盖，而先前的请求仍在处理中。 params 需要移动到 fetch_content 并且 不是 作为参数传递：
import requests
import concurrent.futures
from bs4 import BeautifulSoup
from urllib.parse import urljoin
from threading import Lock
year_list_start = ['2013.01.01','2014.01.02']
year_list_upto = ['2014.01.01','2015.01.01']
base = 'https://search.naver.com/search.naver'
link = 'https://search.naver.com/search.naver'
print_lock = Lock()
def fetch_content(f, s,keyword,link):
params = {
'where': 'news',
'sm': 'tab_pge',
'query': '',
'sort': '1',
'photo': '0',
'field': '0',
'pd': '',
'ds': '',
'de': '',
'cluster_rank': '',
'mynews': '0',
'office_type': '0',
'office_section_code': '0',
'news_office_checked': '',
'nso': '',
'start': '',
}
for start_date,date_upto in zip(year_list_start,year_list_upto):
my_params = params
ds = start_date.replace(".","")
de = date_upto.replace(".","")
my_params['query'] = keyword
my_params['ds'] = ds
my_params['de'] = de
my_params['nso'] = f'so:r,p:from{ds}to{de},a:all'
my_params['start'] = 1
while True:
res = s.get(link,params=my_params)
with print_lock:
print(keyword, res.status_code, file=f)
print(keyword, res.url, file=f, flush=True)
soup = BeautifulSoup(res.text,"lxml")
if not soup.select_one("ul.list_news .news_area .info_group > a.press"): break
for item in soup.select("ul.list_news .news_area"):
newspaper_name = item.select_one(".info_group > a.press").get_text(strip=True).lstrip("=")
with print_lock:
print(keyword, newspaper_name, file=f, flush=True)
if soup.select_one("a.btn_next[aria-disabled='true']"): break
next_page = soup.select_one("a.btn_next").get("href")
link = urljoin(base,next_page)
my_params = None
if __name__ == '__main__':
with requests.Session() as s:
with open('output.txt', 'w', encoding='utf8') as f:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36'
keywords = ['CMG제약','DB하이텍','ES큐브','EV첨단소재']
with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
future_to_url = {executor.submit(fetch_content, f, s, keyword, link): keyword for keyword in keywords}
concurrent.futures.as_completed(future_to_url)
备注
你有...
future_to_url = {executor.submit(fetch_content, s, keyword, link): keyword for keyword in keywords}
concurrent.futures.as_completed(future_to_url)
... 其中 concurrent.futures.as_completed(future_to_url) returns 一个您没有迭代的 迭代器 。您不妨将上面两行替换为：
for keyword in keywords:
executor.submit(fetch_content, s, keyword, link)
或者您可以将 关键字 作为 fetch_content ...
的最后一个参数
def fetch_content(s, link, keyword):
...然后
from functools import partial
executor.map(partial(fetch_content, s, link), keywords)
更新 2
这是一个修改后的版本，其中 fetch_content returns 它找到的报纸名称列表而不是将它们打印出来（然后主线程可以打印列表），其他打印语句是注释掉以减少额外的“噪音”，以便将结果包含在此处。我已经更改了参数的顺序，以防您想使用 map 代替：
import requests
import concurrent.futures
from bs4 import BeautifulSoup
from urllib.parse import urljoin
from functools import partial
year_list_start = ['2013.01.01','2014.01.02']
year_list_upto = ['2014.01.01','2015.01.01']
base = 'https://search.naver.com/search.naver'
link = 'https://search.naver.com/search.naver'
def fetch_content(s, link, keyword):
params = {
'where': 'news',
'sm': 'tab_pge',
'query': '',
'sort': '1',
'photo': '0',
'field': '0',
'pd': '',
'ds': '',
'de': '',
'cluster_rank': '',
'mynews': '0',
'office_type': '0',
'office_section_code': '0',
'news_office_checked': '',
'nso': '',
'start': '',
}
newspaper_names = []
for start_date,date_upto in zip(year_list_start,year_list_upto):
my_params = params
ds = start_date.replace(".","")
de = date_upto.replace(".","")
my_params['query'] = keyword
my_params['ds'] = ds
my_params['de'] = de
my_params['nso'] = f'so:r,p:from{ds}to{de},a:all'
my_params['start'] = 1
while True:
res = s.get(link,params=my_params)
#print(res.status_code, flush=True)
#print(res.url, flush=True)
soup = BeautifulSoup(res.text,"lxml")
if not soup.select_one("ul.list_news .news_area .info_group > a.press"): break
for item in soup.select("ul.list_news .news_area"):
newspaper_name = item.select_one(".info_group > a.press").get_text(strip=True).lstrip("=")
newspaper_names.append(newspaper_name)
if soup.select_one("a.btn_next[aria-disabled='true']"): break
next_page = soup.select_one("a.btn_next").get("href")
link = urljoin(base,next_page)
my_params = None
return newspaper_names
if __name__ == '__main__':
with requests.Session() as s:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36'
keywords = ['CMG제약','DB하이텍','ES큐브','EV첨단소재']
with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
future_to_url = {executor.submit(fetch_content, s, link, keyword): keyword for keyword in keywords}
for future in concurrent.futures.as_completed(future_to_url):
print('keyword = ', future_to_url[future], 'newspaper names =', future.result())
"""
from functools import partial
results = executor.map(partial(fetch_content, s, link), keywords)
for idx, result in enumerate(results):
print('keyword = ', keywords[idx], 'newspaper names =', result)
"""
打印：
keyword = DB하이텍 newspaper names = []
keyword = ES큐브 newspaper names = ['국제신문', '스포츠월드', '스포츠조선', '이뉴스투데이', '중앙SUNDAY', '중앙SUNDAY', '매일경제', '디지털데일리', '전자신문', '머니투데이', '한경비즈니스', '한경비즈니스', '동아일보', '뉴시스', '데일리안', '매일경제', '한경비즈니스', '한경비즈니스', '동아일보', '뉴시스', '데일리안', '매일경제']
keyword = EV첨단소재 newspaper names = ['머니S', '아주경제', 'EBN', '오토타임즈', '머니S', '서울경제', '뉴시스', '파이낸셜뉴스', '연합뉴스', '연합뉴스', 'EBN', '뉴스핌', '포브스코리아', 'EBN', '시민일보', '매일경제', '세계일보', 'TV리포트', '전기신문', '뉴시스', '기호일보', '스포츠월드', 'OSEN', '뉴시스', '경북매일신문', '파이낸셜뉴스', '이투데이', '뉴시스', '헤럴드경제', '헤럴드POP', '조선비즈', 'EBN', '아주경제', '뉴스1', '아시아경제', '헤럴드경제', '전자신문', '뉴시스', '뉴시스', '전기신문', '전자신문', '오토타임즈', '연합뉴스', '에너지경제', '서울경제', 'EBN', '서울경제', '파이낸셜뉴스', '전자신문', '오토타임즈', '연합뉴스', '에너지경제', '서울경제', 'EBN', '서울경제', '파이낸셜뉴스']
keyword = CMG제약 newspaper names = ['국민일보', '국민일보', '메디컬투데이', '한국경제', '서울경제', '매일경제', '시민일보', '아시아경제', '데일리안', '조선비즈', '메디파나뉴스', '매일경제', 'TBS', '매일경제', 'MBN', '아시아경제', 'KBS', '뉴스토마토', '연합뉴스', '뉴스1', '국민일보', '뉴시스', '국민일보', '뉴스토마토', '아시아투데이', '청년의사', '메디파나뉴스', '이데일리', '메디컬투데이', '한국경제', '아시아경제', '이투데이', '머니투데이', '뉴스토마토', '연합뉴스', '약업신문', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '이데일리', '뉴스토마토', '머니투데이', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '머니투데이', '머니투데이', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '이투데이', '한국경제', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '헤럴드POP', '뉴스토마토', '한국경제', '서울경제', '매일경제', '뉴스토마토', '서울파이낸스', '뉴스토마토', '이데일리', '헤럴드POP', '뉴스토마토', '뉴스토마토', '뉴스토마토', '머니투데이', '뉴스토마토', '한국경제', '이투데이', '파이낸셜뉴스', '매일경제', '뉴시스', '뉴스토마토', '뉴스토마토', '이투데이', 'EBN', 'NSP통신', '이투데이', '아주경제', '한국경제', '뉴스핌', '뉴스토마토', '이데일리', '헤럴드POP', '머니투데이', '머니투데이', '아시아경제', 'NSP통신', '서울파이낸스', '아시아경제', '뉴스토마토', '이데일리', '이투데이', '뉴스토마토', '이데일리', '뉴스핌', '머니투데이', '헤럴드POP', '이데일리', '이투데이', '세계일보', '뉴스토마토', '서울파이낸스', '머니투데이', '이데일리', '이투데이', '컨슈머타임스', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '약업신문', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '약업신문', '약업신문', '뉴시스', '연합뉴스', '뉴스토마토', '약업신문', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '약업신문', '약업신문', '한국경제', '서울경제', '이데일리', '이투데이', '한국경제', '매일경제', '이데일리', '서울경제', '매일경제', '이데일리', '서울경제', '이투데이', '파이낸셜뉴스', '조선비즈', '뉴스핌', '한국경제', '머니투데이', '파이낸셜뉴스', '매일경제', '파이낸셜뉴스', '파이낸셜뉴스', '연합뉴스', '데일리팜', '데일리팜', '조선비즈', '이투데이', '한국경제', 'MTN', '서울경제', '뉴스토마토', '메디파나뉴스', '조선비즈', '파이낸셜뉴스', '한국경제', '아시아경제', '이투데이', '연합뉴스', '한국경제', '뉴스핌', '이데일리', '머니투데이', '매일경제', '약업신문', '뉴스토마토', '메디파나뉴스', '파이낸셜뉴스', '파이낸셜뉴스', '한국경제', '이투데이', '머니투데이', '연합뉴스', '이투데이', '매일경제', '매일경제', '뉴스토마토', '서울경제', '이투데이', '아주경제', '이데일리', '한국경제', '헤럴드POP', '매일경제', '뉴스핌', '머니투데이', '머니투데이', '서울파이낸스', '뉴스토마토', '헤럴드POP', '뉴스토마토', '한국경제', '한국경제', '서울경제', '한국경제', '이데일리', '헤럴드POP', '조선비즈', '아주경제', '서울경제', '매일경제', '뉴시스', '뉴스토마토', '뉴스핌', '연합뉴스', '파이낸셜뉴스', '매일경제', '이투데이', '아시아경제', '매일경제', '이투데이', '아시아경제']
备注
如果您取消注释掉其他打印语句 和 您在完成时打印结果（即通过使用方法 as_completed），然后打印输出报纸列表将散布在其他打印行中，可能很难看到。在那种情况下，您可能希望使用我已经包含但已注释掉的 map 方法，以便仅在返回所有结果并发出所有调试打印语句后才打印报纸列表。
我创建了一个脚本，当我使用不同的关键字开始搜索时，从 search engine 中获取不同的报纸名称，如 CMG제약、DB하이텍 e.t.c .在该页面右上角的搜索框中。
我还在参数中使用了一些自定义日期来获取这些日期的结果。只要我在搜索列表中使用 单个关键字 ，脚本就可以正常运行。
但是，当我在搜索列表中使用多个关键字时，脚本只会跟上最后一个关键字。这是我想使用的关键字列表：
keywords = ['CMG제약','DB하이텍','ES큐브','EV첨단소재']
脚本比较短但是因为参数的高度，看起来比较大
到目前为止我已经尝试过 (works as intended as I used single search keyword in the list):
import requests
import concurrent.futures
from bs4 import BeautifulSoup
from urllib.parse import urljoin
year_list_start = ['2013.01.01','2014.01.02']
year_list_upto = ['2014.01.01','2015.01.01']
base = 'https://search.naver.com/search.naver'
link = 'https://search.naver.com/search.naver'
params = {
'where': 'news',
'sm': 'tab_pge',
'query': '',
'sort': '1',
'photo': '0',
'field': '0',
'pd': '',
'ds': '',
'de': '',
'cluster_rank': '',
'mynews': '0',
'office_type': '0',
'office_section_code': '0',
'news_office_checked': '',
'nso': '',
'start': '',
}
def fetch_content(s,keyword,link,params):
for start_date,date_upto in zip(year_list_start,year_list_upto):
ds = start_date.replace(".","")
de = date_upto.replace(".","")
params['query'] = keyword
params['ds'] = ds
params['de'] = de
params['nso'] = f'so:r,p:from{ds}to{de},a:all'
params['start'] = 1
while True:
res = s.get(link,params=params)
print(res.status_code)
print(res.url)
soup = BeautifulSoup(res.text,"lxml")
if not soup.select_one("ul.list_news .news_area .info_group > a.press"): break
for item in soup.select("ul.list_news .news_area"):
newspaper_name = item.select_one(".info_group > a.press").get_text(strip=True).lstrip("=")
print(newspaper_name)
if soup.select_one("a.btn_next[aria-disabled='true']"): break
next_page = soup.select_one("a.btn_next").get("href")
link = urljoin(base,next_page)
params = None
if __name__ == '__main__':
with requests.Session() as s:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36'
keywords = ['CMG제약']
with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
future_to_url = {executor.submit(fetch_content, s, keyword, link, params): keyword for keyword in keywords}
concurrent.futures.as_completed(future_to_url)
How can I make the script work when there are more than one keyword in the search list?
我认为问题在于变量 params 过早地被后续请求的数据覆盖，而先前的请求仍在处理中。 params 需要移动到 fetch_content 并且 不是 作为参数传递：
import requests
import concurrent.futures
from bs4 import BeautifulSoup
from urllib.parse import urljoin
from threading import Lock
year_list_start = ['2013.01.01','2014.01.02']
year_list_upto = ['2014.01.01','2015.01.01']
base = 'https://search.naver.com/search.naver'
link = 'https://search.naver.com/search.naver'
print_lock = Lock()
def fetch_content(f, s,keyword,link):
params = {
'where': 'news',
'sm': 'tab_pge',
'query': '',
'sort': '1',
'photo': '0',
'field': '0',
'pd': '',
'ds': '',
'de': '',
'cluster_rank': '',
'mynews': '0',
'office_type': '0',
'office_section_code': '0',
'news_office_checked': '',
'nso': '',
'start': '',
}
for start_date,date_upto in zip(year_list_start,year_list_upto):
my_params = params
ds = start_date.replace(".","")
de = date_upto.replace(".","")
my_params['query'] = keyword
my_params['ds'] = ds
my_params['de'] = de
my_params['nso'] = f'so:r,p:from{ds}to{de},a:all'
my_params['start'] = 1
while True:
res = s.get(link,params=my_params)
with print_lock:
print(keyword, res.status_code, file=f)
print(keyword, res.url, file=f, flush=True)
soup = BeautifulSoup(res.text,"lxml")
if not soup.select_one("ul.list_news .news_area .info_group > a.press"): break
for item in soup.select("ul.list_news .news_area"):
newspaper_name = item.select_one(".info_group > a.press").get_text(strip=True).lstrip("=")
with print_lock:
print(keyword, newspaper_name, file=f, flush=True)
if soup.select_one("a.btn_next[aria-disabled='true']"): break
next_page = soup.select_one("a.btn_next").get("href")
link = urljoin(base,next_page)
my_params = None
if __name__ == '__main__':
with requests.Session() as s:
with open('output.txt', 'w', encoding='utf8') as f:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36'
keywords = ['CMG제약','DB하이텍','ES큐브','EV첨단소재']
with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
future_to_url = {executor.submit(fetch_content, f, s, keyword, link): keyword for keyword in keywords}
concurrent.futures.as_completed(future_to_url)
备注
你有...
future_to_url = {executor.submit(fetch_content, s, keyword, link): keyword for keyword in keywords}
concurrent.futures.as_completed(future_to_url)
... 其中 concurrent.futures.as_completed(future_to_url) returns 一个您没有迭代的 迭代器 。您不妨将上面两行替换为：
for keyword in keywords:
executor.submit(fetch_content, s, keyword, link)
或者您可以将 关键字 作为 fetch_content ...
def fetch_content(s, link, keyword):
...然后
from functools import partial
executor.map(partial(fetch_content, s, link), keywords)
更新 2
这是一个修改后的版本，其中 fetch_content returns 它找到的报纸名称列表而不是将它们打印出来（然后主线程可以打印列表），其他打印语句是注释掉以减少额外的“噪音”，以便将结果包含在此处。我已经更改了参数的顺序，以防您想使用 map 代替：
import requests
import concurrent.futures
from bs4 import BeautifulSoup
from urllib.parse import urljoin
from functools import partial
year_list_start = ['2013.01.01','2014.01.02']
year_list_upto = ['2014.01.01','2015.01.01']
base = 'https://search.naver.com/search.naver'
link = 'https://search.naver.com/search.naver'
def fetch_content(s, link, keyword):
params = {
'where': 'news',
'sm': 'tab_pge',
'query': '',
'sort': '1',
'photo': '0',
'field': '0',
'pd': '',
'ds': '',
'de': '',
'cluster_rank': '',
'mynews': '0',
'office_type': '0',
'office_section_code': '0',
'news_office_checked': '',
'nso': '',
'start': '',
}
newspaper_names = []
for start_date,date_upto in zip(year_list_start,year_list_upto):
my_params = params
ds = start_date.replace(".","")
de = date_upto.replace(".","")
my_params['query'] = keyword
my_params['ds'] = ds
my_params['de'] = de
my_params['nso'] = f'so:r,p:from{ds}to{de},a:all'
my_params['start'] = 1
while True:
res = s.get(link,params=my_params)
#print(res.status_code, flush=True)
#print(res.url, flush=True)
soup = BeautifulSoup(res.text,"lxml")
if not soup.select_one("ul.list_news .news_area .info_group > a.press"): break
for item in soup.select("ul.list_news .news_area"):
newspaper_name = item.select_one(".info_group > a.press").get_text(strip=True).lstrip("=")
newspaper_names.append(newspaper_name)
if soup.select_one("a.btn_next[aria-disabled='true']"): break
next_page = soup.select_one("a.btn_next").get("href")
link = urljoin(base,next_page)
my_params = None
return newspaper_names
if __name__ == '__main__':
with requests.Session() as s:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36'
keywords = ['CMG제약','DB하이텍','ES큐브','EV첨단소재']
with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
future_to_url = {executor.submit(fetch_content, s, link, keyword): keyword for keyword in keywords}
for future in concurrent.futures.as_completed(future_to_url):
print('keyword = ', future_to_url[future], 'newspaper names =', future.result())
"""
from functools import partial
results = executor.map(partial(fetch_content, s, link), keywords)
for idx, result in enumerate(results):
print('keyword = ', keywords[idx], 'newspaper names =', result)
"""
打印：
keyword = DB하이텍 newspaper names = []
keyword = ES큐브 newspaper names = ['국제신문', '스포츠월드', '스포츠조선', '이뉴스투데이', '중앙SUNDAY', '중앙SUNDAY', '매일경제', '디지털데일리', '전자신문', '머니투데이', '한경비즈니스', '한경비즈니스', '동아일보', '뉴시스', '데일리안', '매일경제', '한경비즈니스', '한경비즈니스', '동아일보', '뉴시스', '데일리안', '매일경제']
keyword = EV첨단소재 newspaper names = ['머니S', '아주경제', 'EBN', '오토타임즈', '머니S', '서울경제', '뉴시스', '파이낸셜뉴스', '연합뉴스', '연합뉴스', 'EBN', '뉴스핌', '포브스코리아', 'EBN', '시민일보', '매일경제', '세계일보', 'TV리포트', '전기신문', '뉴시스', '기호일보', '스포츠월드', 'OSEN', '뉴시스', '경북매일신문', '파이낸셜뉴스', '이투데이', '뉴시스', '헤럴드경제', '헤럴드POP', '조선비즈', 'EBN', '아주경제', '뉴스1', '아시아경제', '헤럴드경제', '전자신문', '뉴시스', '뉴시스', '전기신문', '전자신문', '오토타임즈', '연합뉴스', '에너지경제', '서울경제', 'EBN', '서울경제', '파이낸셜뉴스', '전자신문', '오토타임즈', '연합뉴스', '에너지경제', '서울경제', 'EBN', '서울경제', '파이낸셜뉴스']
keyword = CMG제약 newspaper names = ['국민일보', '국민일보', '메디컬투데이', '한국경제', '서울경제', '매일경제', '시민일보', '아시아경제', '데일리안', '조선비즈', '메디파나뉴스', '매일경제', 'TBS', '매일경제', 'MBN', '아시아경제', 'KBS', '뉴스토마토', '연합뉴스', '뉴스1', '국민일보', '뉴시스', '국민일보', '뉴스토마토', '아시아투데이', '청년의사', '메디파나뉴스', '이데일리', '메디컬투데이', '한국경제', '아시아경제', '이투데이', '머니투데이', '뉴스토마토', '연합뉴스', '약업신문', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '이데일리', '뉴스토마토', '머니투데이', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '머니투데이', '머니투데이', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '이투데이', '한국경제', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '헤럴드POP', '뉴스토마토', '한국경제', '서울경제', '매일경제', '뉴스토마토', '서울파이낸스', '뉴스토마토', '이데일리', '헤럴드POP', '뉴스토마토', '뉴스토마토', '뉴스토마토', '머니투데이', '뉴스토마토', '한국경제', '이투데이', '파이낸셜뉴스', '매일경제', '뉴시스', '뉴스토마토', '뉴스토마토', '이투데이', 'EBN', 'NSP통신', '이투데이', '아주경제', '한국경제', '뉴스핌', '뉴스토마토', '이데일리', '헤럴드POP', '머니투데이', '머니투데이', '아시아경제', 'NSP통신', '서울파이낸스', '아시아경제', '뉴스토마토', '이데일리', '이투데이', '뉴스토마토', '이데일리', '뉴스핌', '머니투데이', '헤럴드POP', '이데일리', '이투데이', '세계일보', '뉴스토마토', '서울파이낸스', '머니투데이', '이데일리', '이투데이', '컨슈머타임스', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '약업신문', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '약업신문', '약업신문', '뉴시스', '연합뉴스', '뉴스토마토', '약업신문', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '뉴스토마토', '약업신문', '약업신문', '한국경제', '서울경제', '이데일리', '이투데이', '한국경제', '매일경제', '이데일리', '서울경제', '매일경제', '이데일리', '서울경제', '이투데이', '파이낸셜뉴스', '조선비즈', '뉴스핌', '한국경제', '머니투데이', '파이낸셜뉴스', '매일경제', '파이낸셜뉴스', '파이낸셜뉴스', '연합뉴스', '데일리팜', '데일리팜', '조선비즈', '이투데이', '한국경제', 'MTN', '서울경제', '뉴스토마토', '메디파나뉴스', '조선비즈', '파이낸셜뉴스', '한국경제', '아시아경제', '이투데이', '연합뉴스', '한국경제', '뉴스핌', '이데일리', '머니투데이', '매일경제', '약업신문', '뉴스토마토', '메디파나뉴스', '파이낸셜뉴스', '파이낸셜뉴스', '한국경제', '이투데이', '머니투데이', '연합뉴스', '이투데이', '매일경제', '매일경제', '뉴스토마토', '서울경제', '이투데이', '아주경제', '이데일리', '한국경제', '헤럴드POP', '매일경제', '뉴스핌', '머니투데이', '머니투데이', '서울파이낸스', '뉴스토마토', '헤럴드POP', '뉴스토마토', '한국경제', '한국경제', '서울경제', '한국경제', '이데일리', '헤럴드POP', '조선비즈', '아주경제', '서울경제', '매일경제', '뉴시스', '뉴스토마토', '뉴스핌', '연합뉴스', '파이낸셜뉴스', '매일경제', '이투데이', '아시아경제', '매일경제', '이투데이', '아시아경제']
备注
如果您取消注释掉其他打印语句 和 您在完成时打印结果（即通过使用方法 as_completed），然后打印输出报纸列表将散布在其他打印行中，可能很难看到。在那种情况下，您可能希望使用我已经包含但已注释掉的 map 方法，以便仅在返回所有结果并发出所有调试打印语句后才打印报纸列表。