feature:全球政治经济新闻
This commit is contained in:
liuwei
@@ -6,11 +6,35 @@ Created Date: 2024-01-21
|
||||
Last Modified: 2024-03-24
|
||||
Modified by: MrCrawL
|
||||
"""
|
||||
from utils.ai.dify_news_analyze import dify_news_title_analyze
|
||||
from utils.markdown_to_image import convert_md_str_to_image
|
||||
|
||||
'''Existing problem: text with hyperlink won't be saved'''
|
||||
|
||||
import requests
|
||||
from time import localtime, sleep
|
||||
from lxml import etree
|
||||
import logging
|
||||
from datetime import datetime
|
||||
|
||||
# 配置日志
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(levelname)s - %(message)s',
|
||||
handlers=[
|
||||
logging.FileHandler(f'news_crawler_{datetime.now().strftime("%Y%m%d")}.log'),
|
||||
logging.StreamHandler()
|
||||
]
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# 请求配置
|
||||
HEADERS = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
|
||||
}
|
||||
TIMEOUT = 10
|
||||
MAX_RETRIES = 3
|
||||
NEWS_LIMIT = 30
|
||||
|
||||
|
||||
def get_time():
|
||||
@@ -18,7 +42,6 @@ def get_time():
|
||||
return date_
|
||||
|
||||
|
||||
# delete duplicated
|
||||
def title_tidy(title_list):
|
||||
t_index = []
|
||||
for i in range(1, len(title_list)):
|
||||
@@ -28,7 +51,6 @@ def title_tidy(title_list):
|
||||
return title_list
|
||||
|
||||
|
||||
# tidy text, seems a little bit redundant
|
||||
def text_tidy(p_text):
|
||||
text_ = p_text.replace('’', "'")
|
||||
text_ = text_.replace(' \n\n', ' ')
|
||||
@@ -46,218 +68,275 @@ def text_tidy(p_text):
|
||||
return text_
|
||||
|
||||
|
||||
def save(text, file_name, mode='w', encoding='utf-8'):
|
||||
with open(f'{file_name}.txt', mode, encoding=encoding) as f: f.write(text)
|
||||
def safe_request(url, retry_count=0):
|
||||
"""安全的请求方法，包含重试机制"""
|
||||
try:
|
||||
response = requests.get(url, headers=HEADERS, timeout=TIMEOUT)
|
||||
response.raise_for_status()
|
||||
return response
|
||||
except requests.RequestException as e:
|
||||
if retry_count < MAX_RETRIES:
|
||||
logger.warning(f"请求失败，正在进行第{retry_count + 1}次重试: {url}")
|
||||
sleep(1)
|
||||
return safe_request(url, retry_count + 1)
|
||||
else:
|
||||
logger.error(f"请求失败: {url}, 错误: {str(e)}")
|
||||
return None
|
||||
|
||||
|
||||
def nbc():
|
||||
url = 'https://www.nbcnews.com/'
|
||||
res = requests.get(url)
|
||||
html = etree.HTML(res.text)
|
||||
href = html.xpath('//h2/a/@href')
|
||||
href = title_tidy(href)
|
||||
# quant = int(input(f'There are {len(href)} pieces detected. How many would you download:'))
|
||||
# if quant > len(href) or quant < 1:
|
||||
# print("Outnumber!")
|
||||
# quit()
|
||||
count = 0
|
||||
# save('', f'NBC_news_title_{get_time()}')
|
||||
# save('', f'NBC_news_text_{get_time()}')
|
||||
msg =''
|
||||
for i in range(30):
|
||||
url = href[i]
|
||||
sleep(0.1) # delete to speed up
|
||||
res = requests.get(url)
|
||||
html = etree.HTML(res.text)
|
||||
title = html.xpath('//h1/text()')
|
||||
if len(title) == 0:
|
||||
print(f'Video or other news. Link: {url}')
|
||||
continue
|
||||
title = title[0]
|
||||
author = html.xpath('//span[@class="byline-name"]/a/text() | //span[@class="byline-name" and not(a)]/text()')
|
||||
author = ', '.join(author)
|
||||
text = html.xpath('//p[@class=""]/text()')
|
||||
text = '\n\n'.join(text)
|
||||
text = text_tidy(text)
|
||||
count += 1
|
||||
# save(f'Title: {title}\nLink: {url}\n\n', f'NBC_news_title_{get_time()}', 'a') # news title
|
||||
# save(f'Title: {title}\n\nOrigin: {url}\n\nAuthor: {author}\n\n\n', f'NBC_news_text_{get_time()}', 'a')
|
||||
# save(f'{text}' + '\n\n------------------------------\n\n', f'NBC_news_text_{get_time()}', 'a')
|
||||
# print(f'Title: {title}. Link: {href[i]}.')
|
||||
msg += f'Title: {title}. Link: {href[i]}.\n'
|
||||
return msg
|
||||
logger.info("开始获取NBC新闻")
|
||||
try:
|
||||
url = 'https://www.nbcnews.com/'
|
||||
response = safe_request(url)
|
||||
if not response:
|
||||
return "获取NBC新闻失败"
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
href = html.xpath('//h2/a/@href')
|
||||
href = title_tidy(href)
|
||||
|
||||
msg = ''
|
||||
count = 0
|
||||
|
||||
for url in href[:NEWS_LIMIT]:
|
||||
try:
|
||||
response = safe_request(url)
|
||||
if not response:
|
||||
continue
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
title = html.xpath('//h1/text()')
|
||||
|
||||
if not title:
|
||||
logger.warning(f'跳过视频或其他类型新闻: {url}')
|
||||
continue
|
||||
|
||||
title = title[0]
|
||||
msg += f'Title: {title}. Link: {url}\n'
|
||||
count += 1
|
||||
sleep(0.1)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"处理新闻失败: {url}, 错误: {str(e)}")
|
||||
continue
|
||||
|
||||
logger.info(f"NBC新闻获取完成，共获取{count}条")
|
||||
return msg
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"获取NBC新闻失败: {str(e)}")
|
||||
return "获取新闻失败，请查看日志了解详情"
|
||||
|
||||
|
||||
def cnn():
|
||||
head = 'https://www.cnn.com'
|
||||
res = requests.get(head + '/')
|
||||
html = etree.HTML(res.text)
|
||||
href = html.xpath('//a[@data-link-type="article"]/@href')
|
||||
href = title_tidy(href)
|
||||
# quant = int(input(f'{len(href)} data detected. How many would you like to download:'))
|
||||
# if quant > len(href) or quant < 1:
|
||||
# print("Outnumber!")
|
||||
# quit()
|
||||
count = 0
|
||||
msg = ''
|
||||
# save('', f'CNN_news_title_{get_time()}')
|
||||
# save('', f'CNN_news_text_{get_time()}')
|
||||
for i in range(30):
|
||||
url = head + href[i]
|
||||
sleep(0.1) # delete to speed up
|
||||
res = requests.get(url)
|
||||
html = etree.HTML(res.text)
|
||||
title = html.xpath('//h1[@data-editable="headlineText"]/text()')
|
||||
if len(title) == 0:
|
||||
print(f'Video or other news. Link: {url}')
|
||||
continue
|
||||
title = title[0].strip()
|
||||
author = html.xpath('//span[@class="byline__name"]/text()')
|
||||
author = ', '.join(author)
|
||||
text = html.xpath('//p[@class="paragraph inline-placeholder"]/text()')
|
||||
for k in range(len(text)): text[k].strip()
|
||||
text = ''.join(text)
|
||||
text = text_tidy(text)
|
||||
count += 1
|
||||
# save(f'Title: {title}\nLink: {url}\n\n', f'CNN_news_title_{get_time()}', 'a') # news title
|
||||
# save(f'Title: {title}\n\nOrigin: {url}\n\nAuthor: {author}\n\n\n', f'CNN_news_text_{get_time()}', 'a')
|
||||
# save(f'{text}' + '\n\n------------------------------\n\n', f'CNN_news_text_{get_time()}', 'a')
|
||||
# print(f'Title: {title}. Link: {url}')
|
||||
msg +=f'Title: {title}. Link: {url}\n'
|
||||
# print(f'Files saved with {count} articles available.')
|
||||
return msg
|
||||
logger.info("开始获取CNN新闻")
|
||||
try:
|
||||
head = 'https://www.cnn.com'
|
||||
response = safe_request(head + '/')
|
||||
if not response:
|
||||
return "获取CNN新闻失败"
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
href = html.xpath('//a[@data-link-type="article"]/@href')
|
||||
href = title_tidy(href)
|
||||
|
||||
msg = ''
|
||||
count = 0
|
||||
|
||||
for url in href[:NEWS_LIMIT]:
|
||||
try:
|
||||
full_url = head + url
|
||||
response = safe_request(full_url)
|
||||
if not response:
|
||||
continue
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
title = html.xpath('//h1[@data-editable="headlineText"]/text()')
|
||||
|
||||
if not title:
|
||||
logger.warning(f'跳过视频或其他类型新闻: {full_url}')
|
||||
continue
|
||||
|
||||
title = title[0].strip()
|
||||
msg += f'Title: {title}. Link: {full_url}\n'
|
||||
count += 1
|
||||
sleep(0.1)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"处理新闻失败: {full_url}, 错误: {str(e)}")
|
||||
continue
|
||||
|
||||
logger.info(f"CNN新闻获取完成，共获取{count}条")
|
||||
return msg
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"获取CNN新闻失败: {str(e)}")
|
||||
return "获取新闻失败，请查看日志了解详情"
|
||||
|
||||
|
||||
def abc():
|
||||
head = 'https://abcnews.go.com/'
|
||||
res = requests.get(head)
|
||||
html = etree.HTML(res.text)
|
||||
href1 = html.xpath('//div[@class="HeadlinesTrio"]/a/@href')
|
||||
href2 = html.xpath('//div[@class="title card"]/a[@class="AnchorLink"]/@href | //div[@class="title"]/a[@class="AnchorLink"]/@href')
|
||||
href3 = html.xpath('//a[@target="_self"]/@href')
|
||||
href4 = html.xpath('//a[@class="AnchorLink VideoTile"]/@href')
|
||||
href = href1 + href2 + href3 + href4
|
||||
href = title_tidy(href)
|
||||
# quant = int(input(f'{len(href)} data detected. How many would you like to download:'))
|
||||
# if quant > len(href) or quant < 1:
|
||||
# print("Outnumber!")
|
||||
# quit()
|
||||
count = 0
|
||||
msg = ''
|
||||
# save('', f'ABC_news_title_{get_time()}')
|
||||
# save('', f'ABC_news_text_{get_time()}')
|
||||
for i in range(30):
|
||||
url = href[i]
|
||||
sleep(0.1) # delete to speed up
|
||||
res = requests.get(url)
|
||||
html = etree.HTML(res.text)
|
||||
title = html.xpath('//div[@data-testid="prism-headline"]/h1/text()')
|
||||
if len(title) == 0:
|
||||
print(f'Video or other news. Link: {url}')
|
||||
continue
|
||||
title = title[0]
|
||||
author = html.xpath('//a[@data-testid="prism-linkbase"]/text()')
|
||||
author = ', '.join(author)
|
||||
text = html.xpath('//div[@data-testid="prism-article-body"]/p/text()')
|
||||
text = '\n\n'.join(text)
|
||||
text = text_tidy(text)
|
||||
count += 1
|
||||
# save(f'Title: {title}\nLink: {url}\n\n', f'ABC_news_title_{get_time()}', 'a') # news title
|
||||
# save(f'Title: {title}\n\nOrigin: {url}\n\nAuthor: {author}\n\n\n', f'ABC_news_text_{get_time()}', 'a')
|
||||
# save(f'{text}' + '\n\n------------------------------\n\n', f'ABC_news_text_{get_time()}', 'a')
|
||||
# print(f'Title: {title}. Link: {url}')
|
||||
msg +=f'Title: {title}. Link: {url}\n'
|
||||
# print(f'Files saved with {count} articles available.')
|
||||
return msg
|
||||
logger.info("开始获取ABC新闻")
|
||||
try:
|
||||
head = 'https://abcnews.go.com' # 移除末尾的斜杠
|
||||
response = safe_request(head)
|
||||
if not response:
|
||||
return "获取ABC新闻失败"
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
href1 = html.xpath('//div[@class="HeadlinesTrio"]/a/@href')
|
||||
href2 = html.xpath(
|
||||
'//div[@class="title card"]/a[@class="AnchorLink"]/@href | //div[@class="title"]/a[@class="AnchorLink"]/@href')
|
||||
href3 = html.xpath('//a[@target="_self"]/@href')
|
||||
href4 = html.xpath('//a[@class="AnchorLink VideoTile"]/@href')
|
||||
href = title_tidy(href1 + href2 + href3 + href4)
|
||||
|
||||
msg = ''
|
||||
count = 0
|
||||
|
||||
for url in href[:NEWS_LIMIT]:
|
||||
try:
|
||||
# 处理URL格式
|
||||
if url.startswith('http'):
|
||||
full_url = url
|
||||
elif url.startswith('//'):
|
||||
full_url = 'https:' + url
|
||||
else:
|
||||
full_url = head + ('' if url.startswith('/') else '/') + url
|
||||
|
||||
response = safe_request(full_url)
|
||||
if not response:
|
||||
continue
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
title = html.xpath('//div[@data-testid="prism-headline"]/h1/text()')
|
||||
|
||||
if not title:
|
||||
logger.warning(f'跳过视频或其他类型新闻: {full_url}')
|
||||
continue
|
||||
|
||||
title = title[0]
|
||||
msg += f'Title: {title}. Link: {full_url}\n'
|
||||
count += 1
|
||||
sleep(0.1)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"处理新闻失败: {full_url}, 错误: {str(e)}")
|
||||
continue
|
||||
|
||||
logger.info(f"ABC新闻获取完成，共获取{count}条")
|
||||
return msg
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"获取ABC新闻失败: {str(e)}")
|
||||
return "获取新闻失败，请查看日志了解详情"
|
||||
|
||||
|
||||
def fox():
|
||||
head = 'https://www.foxnews.com/'
|
||||
res = requests.get(head)
|
||||
html = etree.HTML(res.text)
|
||||
href = html.xpath('//h3[@class="title"]/a/@href')
|
||||
href = title_tidy(href)
|
||||
# quant = int(input(f'{len(href)} data detected. How many would you like to download:'))
|
||||
# if quant > len(href) or quant < 1:
|
||||
# print("Outnumber!")
|
||||
# quit()
|
||||
count = 0
|
||||
msg =''
|
||||
# save('', f'FOX_news_title_{get_time()}')
|
||||
# save('', f'FOX_news_text_{get_time()}')
|
||||
for i in range(30):
|
||||
if href[i][0:4] != 'http': href[i] = 'https:' + href[i]
|
||||
url = href[i]
|
||||
sleep(0.1) # delete to speed up
|
||||
res = requests.get(url)
|
||||
html = etree.HTML(res.text)
|
||||
title = html.xpath('//h1[@itemprop="headline"]/text()')
|
||||
if len(title) == 0:
|
||||
print(f'Video or other news. Link: {url}')
|
||||
continue
|
||||
title = title[0]
|
||||
author = html.xpath('//a[@rel="author"]/strong/text()')
|
||||
author = ', '.join(author)
|
||||
text = html.xpath('//div[@itemprop="articleBody"]/p/text()')
|
||||
text = '\n\n'.join(text)
|
||||
text = text_tidy(text)
|
||||
count += 1
|
||||
# save(f'Title: {title}\nLink: {url}\n\n', f'FOX_news_title_{get_time()}', 'a') # news title
|
||||
# save(f'Title: {title}\n\nOrigin: {url}\n\nAuthor: {author}\n\n\n', f'FOX_news_text_{get_time()}', 'a')
|
||||
# save(f'{text}' + '\n\n------------------------------\n\n', f'FOX_news_text_{get_time()}', 'a')
|
||||
# print(f'Title: {title}. Link: {url}')
|
||||
msg +=f'Title: {title}. Link: {url}\n'
|
||||
# print(f'Files saved with {count} articles available.')
|
||||
return msg
|
||||
logger.info("开始获取FOX新闻")
|
||||
try:
|
||||
head = 'https://www.foxnews.com/'
|
||||
response = safe_request(head)
|
||||
if not response:
|
||||
return "获取FOX新闻失败"
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
href = html.xpath('//h3[@class="title"]/a/@href')
|
||||
href = title_tidy(href)
|
||||
|
||||
msg = ''
|
||||
count = 0
|
||||
|
||||
for url in href[:NEWS_LIMIT]:
|
||||
try:
|
||||
if url[0:4] != 'http':
|
||||
url = 'https:' + url
|
||||
|
||||
response = safe_request(url)
|
||||
if not response:
|
||||
continue
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
title = html.xpath('//h1[@itemprop="headline"]/text()')
|
||||
|
||||
if not title:
|
||||
logger.warning(f'跳过视频或其他类型新闻: {url}')
|
||||
continue
|
||||
|
||||
title = title[0]
|
||||
msg += f'Title: {title}. Link: {url}\n'
|
||||
count += 1
|
||||
sleep(0.1)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"处理新闻失败: {url}, 错误: {str(e)}")
|
||||
continue
|
||||
|
||||
logger.info(f"FOX新闻获取完成，共获取{count}条")
|
||||
return msg
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"获取FOX新闻失败: {str(e)}")
|
||||
return "获取新闻失败，请查看日志了解详情"
|
||||
|
||||
|
||||
def bbc():
|
||||
head = 'https://www.bbc.com'
|
||||
res = requests.get(head + '/')
|
||||
html = etree.HTML(res.text)
|
||||
href = html.xpath('//h2[@data-testid="card-headline"]/../../../../../@href | //h2[@data-testid="card-headline"]/../../../../@href')
|
||||
href = title_tidy(href)
|
||||
# quant = int(input(f'{len(href)} data detected. How many would you like to download:'))
|
||||
# if quant > len(href) or quant < 1:
|
||||
# print("Outnumber!")
|
||||
# quit()
|
||||
count = 0
|
||||
msg =''
|
||||
# save('', f'BBC_news_title_{get_time()}')
|
||||
# save('', f'BBC_news_text_{get_time()}')
|
||||
for i in range(30):
|
||||
if href[i][0:4] == 'http': continue
|
||||
url = head + href[i]
|
||||
sleep(0.1) # delete to speed up
|
||||
print(url)
|
||||
res = requests.get(url)
|
||||
html = etree.HTML(res.text)
|
||||
title = html.xpath('//div[@data-component="headline-block"]/h1/text()')
|
||||
if len(title) == 0:
|
||||
# print(f'Video or other news. Link: {url}')
|
||||
continue
|
||||
title = title[0]
|
||||
# author = html.xpath('//div[@data-testid="byline"]/div/span[@data-testid="byline-name"]/text()')
|
||||
# author = ', '.join(author)
|
||||
# text = html.xpath('//div[@data-component="text-block"]/p/b/text() | //div[@data-component="text-block"]/p/text()')
|
||||
# text = '\n\n'.join(text)
|
||||
# text = text_tidy(text)
|
||||
count += 1
|
||||
# save(f'Title: {title}\nLink: {url}\n\n', f'BBC_news_title_{get_time()}', 'a') # news title
|
||||
# save(f'Title: {title}\n\nOrigin: {url}\n\nAuthor: {author}\n\n\n', f'BBC_news_text_{get_time()}', 'a')
|
||||
# save(f'{text}' + '\n\n------------------------------\n\n', f'BBC_news_text_{get_time()}', 'a')
|
||||
# print(f'Title: {title}. Link: {url}')
|
||||
logger.info("开始获取BBC新闻")
|
||||
try:
|
||||
head = 'https://www.bbc.com'
|
||||
response = safe_request(head + '/')
|
||||
if not response:
|
||||
return "获取BBC新闻失败"
|
||||
|
||||
msg +=f'Title: {title}. Link: {url}\n'
|
||||
# print(f'Files saved with {count} articles available.')
|
||||
return msg
|
||||
html = etree.HTML(response.text)
|
||||
href = html.xpath(
|
||||
'//h2[@data-testid="card-headline"]/../../../../../@href | //h2[@data-testid="card-headline"]/../../../../@href')
|
||||
href = title_tidy(href)
|
||||
|
||||
if __name__ == '__main__':
|
||||
# Hello, World! :)
|
||||
# news = input('Choose news site["nbc","cnn","abc","fox","bbc"]:').lower()
|
||||
# if news == 'nbc': nbc()
|
||||
# elif news == 'cnn': cnn()
|
||||
# elif news == 'abc': abc()
|
||||
# elif news == 'fox': fox()
|
||||
# elif news == 'bbc': bbc()
|
||||
# else:
|
||||
# print('Oops! It seems a wrong input. Please retry...')
|
||||
# sleep(2)
|
||||
print(bbc())
|
||||
msg = ''
|
||||
count = 0
|
||||
|
||||
for url in href[:NEWS_LIMIT]:
|
||||
try:
|
||||
if url[0:4] == 'http':
|
||||
continue
|
||||
|
||||
full_url = head + url
|
||||
response = safe_request(full_url)
|
||||
if not response:
|
||||
continue
|
||||
|
||||
html = etree.HTML(response.text)
|
||||
title = html.xpath('//div[@data-component="headline-block"]/h1/text()')
|
||||
|
||||
if not title:
|
||||
logger.warning(f'跳过视频或其他类型新闻: {full_url}')
|
||||
continue
|
||||
|
||||
title = title[0]
|
||||
msg += f'Title: {title}. Link: {full_url}\n'
|
||||
count += 1
|
||||
sleep(0.1)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"处理新闻失败: {full_url}, 错误: {str(e)}")
|
||||
continue
|
||||
|
||||
logger.info(f"BBC新闻获取完成，共获取{count}条")
|
||||
return msg
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"获取BBC新闻失败: {str(e)}")
|
||||
return "获取新闻失败，请查看日志了解详情"
|
||||
|
||||
|
||||
def all_english_news():
|
||||
news_titles = ""
|
||||
news_titles += nbc() + "\n"
|
||||
news_titles += cnn() + "\n"
|
||||
news_titles += abc() + "\n"
|
||||
news_titles += fox() + "\n"
|
||||
news_titles += bbc() + "\n"
|
||||
markdown_news = dify_news_title_analyze(news_titles)
|
||||
spath = convert_md_str_to_image(markdown_news, "news_output.png")
|
||||
return spath
|
||||
|
||||
@@ -11,6 +11,7 @@ import requests
|
||||
from lxml import etree
|
||||
|
||||
from base import func_english_news
|
||||
from utils.ai.dify_news_analyze import dify_news_title_analyze
|
||||
|
||||
|
||||
class News(object):
|
||||
@@ -70,10 +71,10 @@ class News(object):
|
||||
post = response.json()
|
||||
# 提取content列表 - 避免使用str作为变量名
|
||||
content_list = post.get('data', {}).get('cards', [])
|
||||
|
||||
|
||||
if content_list and len(content_list) > 0:
|
||||
news_items = content_list[0].get('content', [])
|
||||
|
||||
|
||||
# 遍历列表，并格式化每个字典的title, url，然后添加到output字符串中
|
||||
for index, article in enumerate(news_items, start=1):
|
||||
if isinstance(article, dict) and 'word' in article:
|
||||
@@ -81,34 +82,34 @@ class News(object):
|
||||
# url = article.get('url', '')
|
||||
# 使用f-string格式化字符串，并添加到output中
|
||||
output += f"{index} :#{title}\n"
|
||||
|
||||
|
||||
# 输出最终的字符串
|
||||
return output
|
||||
else:
|
||||
self.LOG.error(f"获取百度新闻失败，状态码: {response.status_code}")
|
||||
return "获取百度新闻失败，请稍后再试"
|
||||
|
||||
|
||||
except Exception as e:
|
||||
self.LOG.error(f"获取百度新闻时出错: {e}")
|
||||
return f"获取百度新闻时出错: {e}"
|
||||
|
||||
def get_eng_news(self,website):
|
||||
def get_eng_news(self, website):
|
||||
if website == 'nbc':
|
||||
return func_english_news.nbc()
|
||||
return func_english_news.nbc()
|
||||
elif website == 'cnn':
|
||||
return func_english_news.cnn()
|
||||
return func_english_news.cnn()
|
||||
elif website == 'abc':
|
||||
return func_english_news.abc()
|
||||
elif website == 'fox':
|
||||
return func_english_news.fox()
|
||||
elif website == 'bbc':
|
||||
return func_english_news.bbc()
|
||||
return func_english_news.bbc()
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
news = News()
|
||||
print(news.get_baidu_news())
|
||||
# # msg = "@水牛-分身 今日百度新闻"
|
||||
# # q = re.sub(r"@.*?[\u2005|\s]", "", msg).replace(" ", "")
|
||||
# # print(q)
|
||||
# print(news.get_eng_news('nbc'))
|
||||
# print(news.get_eng_news('nbc'))
|
||||
|
||||
Reference in New Issue
Block a user