响应巨蟒侠，分享一下前一段弄得一个自动爬某站bt的脚本吧
本帖最后由 革萌 于 2021-1-12 22:12 编辑基本上Cookie那一行换成自己的就行
nas_url = "http://192.168.50.136:8888/transfers/action"这一行需要改成自己的tixati的webui地址，session.verify视自己的网络情况看是否需要。（感谢一楼提醒）
解释一下哈 这个脚本是需要随便写个守护进程来周期性运行的，比如每小时执行一次，自动把最下面url列表里的url抓一边，把抓到的种子丢到下载器去下载。
不过我跑了一个月，下了几百G完全不想看的图集，最后硬盘还坏了
比如把python代码存成ex.py的话，随便写个bat
:loop
python ex.py
sleep 3600
goto loop
忘了说，下载用的是tixati，这个bt下载器带一个web ui，换成aria2也是没啥问题的，只是需要改一下提交下载任务的代码
import requests
import bs4
import re
import sqlite3
from datetime import datetime
from requests.packages.urllib3.util.retry import Retry
from requests.adapters import HTTPAdapter
def get_time():
now = datetime.now()# current date and time
return now.strftime("%m/%d/%Y, %H:%M:%S")
conn = sqlite3.connect('exhentai.db')
c = conn.cursor()
c.execute("""CREATE TABLE IF NOT EXISTS gallerys (
name TEXTNOT NULL,
url TEXTNOT NULL,
gid TEXT PRIMARY KEYNOT NULL,
tor_url TEXT,
modified_date TEXT
)""")
c.execute("""CREATE TABLE IF NOT EXISTS gallerys_tor (
gid TEXTNOT NULL,
tor_url TEXT,
hash TEXT PRIMARY KEY NOT NULL,
filename TEXT,
seeds INTEGER ,
file_size REAL,
upload_date TEXT,
modified_date TEXT
)""")
c.execute("""CREATE TABLE IF NOT EXISTS tor_task (
hash TEXT PRIMARY KEY NOT NULL,
url TEXT,
status TEXT,
modified_date TEXT
)""")
headers = {
"Connection": "keep-alive",
"Cache-Control": "max-age=0",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"Sec-Fetch-Site": "same-origin",
"Sec-Fetch-Mode": "navigate",
"Sec-Fetch-User": "?1",
"Sec-Fetch-Dest": "document",
"Referer": "https://exhentai.org/",
"Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7",
"Cookie": "ipb_member_id=; ipb_pass_hash=; igneous=; sl=dm_1; sk=; u="
}
session = requests.Session()
session.keep_alive = False
session.verify = 'GotoXCA.crt'
retry = Retry(connect=30, backoff_factor=0.5)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)
def addTask(tor_file_url):
print("下载种子 " + tor_file_url)
hash = re.search("https://exhentai\.org/torrent/\d+/([\da-z]+)\.torrent\?p=[\da-z-]+", tor_file_url).group(1)
c.execute("select count(1) from tor_task where hash = '"+hash+"'")
result=c.fetchone()
if(result>0):
return
r = session.get(tor_file_url, headers=headers)
if (r.status_code == 200):
nas_url = "http://192.168.50.136:8888/transfers/action"
files = {'metafile': r.content}
data = {'noautostart': "0", "addmetafile": "Add"}
add_res=session.post(nas_url, files=files, data=data)
if(add_res == 200):
print("添加任务成功")
c.execute( "insert into tor_task (hash,url,status,modified_date) VALUES(?, ?, ?,?) ",(hash,tor_file_url,"Add", get_time()))
conn.commit()
def processTor(tor_page_url):
print("process "+tor_page_url)
r = session.get(tor_page_url, headers=headers)
if(r.status_code==200):
gid_1 = re.search("https://exhentai\.org/gallerytorrents\.php\?gid=(\d+)", tor_page_url).group(1)
doc = bs4.BeautifulSoup(r.text,features="html.parser")
torlist=[]
for f in doc.select("form"):
if(len(f.select("div table tr td")))>3 and f.select("div table tr").select_one("td a") != None:
tor_url = re.search("document\.location='([^']+)",f.select("div table tr").select_one("td a")["onclick"]).group(1)
tor_filename = f.select("div table tr").select_one("td a").text
tor_upload_date = re.search("Posted:\s([\d\s:-]+)",f.select("div table tr td").text).group(1)
tor_size = re.search("Size:\s(.+)",f.select("div table tr td").text).group(1)
tor_seed = re.search("Seeds:\s(\d+)",f.select("div table tr td").text).group(1)
hash = re.search("https://exhentai\.org/torrent/\d+/([\da-z]+)\.torrent\?p=[\da-z-]+",tor_url).group(1)
torlist.append({"upload_time":tor_upload_date,"tor_url":tor_url})
c.execute("replace into gallerys_tor (gid,tor_url,seeds,file_size,upload_date,modified_date,hash,filename) VALUES(?, ?, ?, ?,?,?,?,?) ", ( gid_1, tor_url,tor_seed,tor_size, tor_upload_date , get_time(),hash,tor_filename))
conn.commit()
addTask(sorted(torlist, key=lambda i:datetime.strptime(i['upload_time'],"%Y-%m-%d %H:%M"))[-1]["tor_url"])
def processPage(page_url):
print("处理页面 "+page_url)
r = session.get(page_url, headers=headers)
if (r.status_code == 200):
doc = bs4.BeautifulSoup(r.text,features="html.parser")
file_entrys = doc.select(".gl1t")
for file_entry in file_entrys:
name = file_entry.select_one(".gl3t a img")['title']
url = file_entry.select_one(".gl3t a")['href']
gid = re.search("https://exhentai\.org/g/(\d+)", url).group(1)
tor_url_a = file_entry.select_one(".gldown a")
if tor_url_a is None:
tor_url = ""
else:
tor_url = re.search("return\spopUp\('([^']+)", tor_url_a['onclick']).group(1)
processTor(tor_url)
c.execute("replace into gallerys VALUES(?, ?, ?, ?,?) ", (name, url, gid, tor_url,get_time()))
conn.commit()
def processTask(url_arr):
for url in url_arr:
processPage(url)
watch_urls=[
"https://exhentai.org/watched?page=11",
"https://exhentai.org/watched?page=10",
"https://exhentai.org/watched?page=9",
"https://exhentai.org/watched?page=8",
"https://exhentai.org/watched?page=7",
"https://exhentai.org/watched?page=6",
"https://exhentai.org/watched?page=5",
"https://exhentai.org/watched?page=4",
"https://exhentai.org/watched?page=3",
"https://exhentai.org/watched?page=2",
"https://exhentai.org/watched?page=1",
"https://exhentai.org/watched"
]
pop_urls = [
"https://exhentai.org/popular"
]
processTask(pop_urls)
processTask(watch_urls)
nessaj 发表于 2021-1-12 20:48
你这需要替换的地方有点多吧...
不说硬性的
我似乎没找到关键字Filter在哪里设置呀.... ...
e站的filter是用url传的
nessaj 发表于 2021-1-12 21:41
那么怎么自定义filter呢
https://exhentai.org/?page=1&f_search=+language:chinese
这么写就行了 为什么巨蟒侠的帖子那么多人回，我的贴子连巨蟒侠都不回。来几个人拍死我也好啊。 手动挑artbook中，毕竟多数也不想要
—— 来自 Xiaomi MIX 2S, Android 10上的 S1Next-鹅版 v2.4.4 祸猫 发表于 2021-1-20 22:23
手动挑artbook中，毕竟多数也不想要
—— 来自 Xiaomi MIX 2S, Android 10上的 S1Next-鹅版 v2.4.4 ...
我准备写个从我的收藏里扩散，找最有可能感兴趣的gallery
页:
[1]