zhenxun_bot/plugins/search_anime/data_source.py

63 lines
2.3 KiB
Python
Raw Normal View History

2021-05-20 19:23:32 +08:00
from lxml import etree
2021-08-17 23:17:08 +08:00
from lxml import etree
2021-05-20 19:23:32 +08:00
import feedparser
from urllib import parse
from services.log import logger
import aiohttp
import time
2021-06-30 19:50:55 +08:00
from utils.utils import get_local_proxy
2021-05-20 19:23:32 +08:00
2021-07-30 21:21:51 +08:00
async def from_anime_get_info(key_word: str, max_: int) -> str:
2021-05-20 19:23:32 +08:00
s_time = time.time()
repass = ""
2021-07-30 21:21:51 +08:00
url = "https://share.dmhy.org/topics/rss/rss.xml?keyword=" + parse.quote(key_word)
2021-05-20 19:23:32 +08:00
try:
logger.debug("Now starting get the {}".format(url))
2021-07-30 21:21:51 +08:00
repass = await get_repass(url, max_)
2021-05-20 19:23:32 +08:00
except Exception as e:
logger.error("Timeout! {}".format(e))
return f"搜索 {key_word} 结果(耗时 {int(time.time() - s_time)} 秒):\n" + repass
2021-07-30 21:21:51 +08:00
async def get_repass(url: str, max_: int) -> str:
2021-05-20 19:23:32 +08:00
putline = []
async with aiohttp.ClientSession() as session:
async with session.get(url, proxy=get_local_proxy(), timeout=20) as response:
d = feedparser.parse(await response.text())
2021-07-30 21:21:51 +08:00
url_list = [e.link for e in d.entries][:max_]
2021-05-20 19:23:32 +08:00
for u in url_list:
print(u)
try:
2021-07-30 21:21:51 +08:00
async with session.get(
u, proxy=get_local_proxy(), timeout=20
) as res:
2021-05-20 19:23:32 +08:00
html = etree.HTML(await res.text())
magent = html.xpath('.//a[@id="a_magnet"]/text()')[0]
2021-07-30 21:21:51 +08:00
title = html.xpath(".//h3/text()")[0]
item = html.xpath(
'//div[@class="info resource-info right"]/ul/li'
)
class_a = (
item[0]
.xpath("string(.)")[5:]
.strip()
.replace("\xa0", "")
.replace("\t", "")
)
size = item[3].xpath("string(.)")[5:].strip()
putline.append(
"{}】| {}\n{}】| {}".format(class_a, title, size, magent)
)
2021-05-20 19:23:32 +08:00
except Exception as e:
2021-07-30 21:21:51 +08:00
logger.warning(f"搜番超时 e{e}")
2021-05-20 19:23:32 +08:00
2021-07-30 21:21:51 +08:00
repass = "\n\n".join(putline)
2021-05-20 19:23:32 +08:00
return repass
2021-07-30 21:21:51 +08:00
# print(asyncio.get_event_loop().run_until_complete(from_anime_get_info('进击的巨人', 1234556)))