Linux-Gaming/bot-news-linux-gaming
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Добавлена публикация в VK

Browse Source
This commit is contained in:
Евгений Храмов
2024-05-26 19:45:26 +03:00
parent c9fddc25f6
commit 8f79abddbf
2 changed files with 76 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

110
news-bot.py
View File

@@ -26,15 +26,16 @@ heads_site = {
}
params_get = {
'access_token': keys.api_key_vk,
'v': '5.199', # Версия API
'owner_id': keys.own_id,
'count': 100,
'offset': 0
'access_token': keys.user_token_vk,
'v': '5.236', # Версия API
'owner_id': str(keys.own_id),
'count': str(100),
'offset': str(0),
'filter': 'all'
}
logger = logging.getLogger()
logger.setLevel(logging.DEBUG)
logger.setLevel(logging.INFO)
handler = colorlog.StreamHandler()
handler.setFormatter(colorlog.ColoredFormatter(
@@ -70,7 +71,7 @@ def html_to_text(html_content):
h.reference_links = True # Сохранение оригинальных ссылок
markdown_text = h.handle(html_content)
logging.debug(f"Markdown text для дискорд: {markdown_text}")
logging.debug(f"Markdown text: {markdown_text}")
# Удаление переносов строк из-за -
markdown_text = re.sub(r'-\s*\n\s*', '-', markdown_text, flags=re.DOTALL)
@@ -103,7 +104,7 @@ def html_to_text(html_content):
# Удаление избыточных пустых строк после удаления строк
markdown_text = re.sub(r'\n\s*\n', '\n', markdown_text)
#Изменение ссылок без описания
# Изменение ссылок без описания
markdown_text = re.sub(r'\[\]\((https:\/\/[^\)]+)\)', r'[content](\1)', markdown_text)
markdown_text = re.sub(r'\[\s]\((https:\/\/[^\)]+)\)', r'[content](\1)', markdown_text)
@@ -120,6 +121,12 @@ def remove_empty_lines(text_data):
return '\n'.join(non_empty_lines)
def remove_markdown_links(markdown_text):
# Регулярное выражение для поиска Markdown-ссылок и замена их на только URL
markdown_text = re.sub(r'\[.*?\]\((https?://.*?)\)', r'\1' or r'(`https?://.*?)`\)', markdown_text)
return markdown_text
def remove_duplicate_links(text):
seen_links = set()
@@ -137,6 +144,12 @@ def remove_duplicate_links(text):
return text
def extract_links(text):
# Регулярное выражение для поиска ссылок
url_pattern = re.compile(r'https?://\S+')
return url_pattern.findall(text)
def script_content(script_ver, resp_changelog):
soup = make_soup(resp_changelog)
page_text = str(soup)
@@ -158,6 +171,8 @@ def script_content(script_ver, resp_changelog):
site_text = (f"[center][img]/uploads/default/original/1X/5cfa59077a5275971401fab0114e56f3ffdd0ec4.png[/img]["
f"/center]\n{post_text}")
logging.debug(f"Сообщение на сайт {site_text}")
post_data = {
"title": f"Обновление скриптов {script_ver}",
"raw": site_text,
@@ -165,7 +180,6 @@ def script_content(script_ver, resp_changelog):
"tags": ["scripts"]
}
return post_text, post_data, post_text
@@ -180,7 +194,6 @@ def news_content(post_id):
if post.get('post_number') == 1:
html_content = post.get('cooked', 'Нет содержимого')
text_data = html_to_text(html_content)
logging.debug(text_data)
return text_data
logging.error(f"Первый пост не найден в теме с ID: {post_id}")
return None
@@ -191,7 +204,10 @@ def news_content(post_id):
def response_get(url, heads_site):
try:
return requests.get(url, headers=heads_site)
if heads_site == params_get:
return requests.get(url, params=params_get)
elif heads_site == heads_site:
return requests.get(url, headers=heads_site)
except requests.RequestException as err:
logging.error(f"Ошибка запроса {err}")
@@ -211,12 +227,8 @@ def resp_change():
return None, None
def resp_get(url, heads_site):
return response_get(url, heads_site=heads_site)
def news():
resp_topics = resp_get(url_news, heads_site)
resp_topics = response_get(url_news, heads_site)
if resp_topics.status_code == 200:
data = resp_topics.json()
@@ -344,15 +356,18 @@ def check_discord_public():
client.run(keys.discord_token)
def vk_post(url, post_text):
def vk_post(url, post_text, links=None):
params_post = {
'access_token': keys.api_key_vk,
'v': '5.199', # Версия API VK
'owner_id': keys.own_id,
'message': f'{post_text}',
'attachments': "photo-99238527_457244491"
'v': '5.236', # Версия API VK
'owner_id': str(keys.own_id),
'message': f'{post_text}'
# Дополнительные параметры можно добавить здесь
}
if links:
params_post['attachments'] = links
try:
# Отправляем POST-запрос к VK API
resp_post = requests.post(url=url, params=params_post)
@@ -369,35 +384,49 @@ def vk_post(url, post_text):
return None
def vk_topics():
def get_vk_topics():
wall_posts = []
while True:
wall_data = response_get(url_vk_get, heads_site=params_get)
if not wall_data:
logging.warning(f"Постов на стене нет")
wall_posts.extend((post['text'] for post in wall_data if 'text' in post))
wall_data = response_get(url_vk_get, params_get)
wall_data_json = wall_data.json()
if 'error' in wall_data_json:
error_code = wall_data_json['error']['error_code']
error_msg = wall_data_json['error']['error_msg']
logging.error(f"Ошибка {error_code}: {error_msg}")
sys.exit(f"Ошибка {error_code}: {error_msg}")
if len(wall_data) < 100:
items = wall_data_json.get('response', {}).get('items', [])
if not items:
logging.warning("Постов на стене нет")
break
heads_site['offset'] += 100
wall_posts.extend((post['text'] for post in items if 'text' in post))
if len(items) < 100:
break
params_get['offset'] = str(int(params_get['offset']) + 100)
pattern = re.compile(r'----------------------------------------------------------\n### (.*?)\t\n', re.DOTALL)
for message in wall_posts:
matches = pattern.findall(message)
if matches:
wall_posts.extend(matches)
logging.debug(f"Найдены посты в ВК: {wall_posts}")
return wall_posts
def check_vk_posts():
vk_posts = vk_topics()
vk_posts = get_vk_topics()
if not vk_posts:
logging.warning(f"Постов на стене нет")
else:
logging.debug(f"Посты из VK {vk_posts}")
logging.warning(f"Постов на стене нет{vk_posts}")
list_titles_and_ids = news()
if list_titles_and_ids:
list_for_public = []
for topic_id, topic_title in list_titles_and_ids:
if topic_title not in vk_posts():
# Сравнение заголовков с текстами постов
if not any(topic_title in vk_posts for vk_posts in vk_posts):
list_for_public.append((topic_id, topic_title))
if not list_for_public:
logging.info(f"Новостей для публикации в ВК нет")
@@ -406,8 +435,17 @@ def check_vk_posts():
for topic_id, topic_title in reversed(list_for_public):
text_data = news_content(topic_id)
if text_data:
content = f"----------------------------------------------------------\n### {topic_title}\t\n" + text_data + "\n"
vk_post(url_vk_post, content)
content = f"----------------------------------------------------------\n{topic_title}\t\n" + text_data + "\n"
content = remove_markdown_links(content)
links = extract_links(content)
if "Обновление скриптов" in topic_title:
# Пример добавления изображения с постом
vk_post(url_vk_post, content, "photo-99238527_457244491")
else:
if links:
vk_post(url_vk_post, content, links)
else:
vk_post(url_vk_post, content)
if __name__ == '__main__':