from fake_useragent import UserAgent
import requests,os,json
from lxml import html
import traceback
import time,re
from urllib3.util.retry import Retry
from requests.adapters import HTTPAdapter
from utils.Ntfy import ntfy
from utils.comic.PathStr import pathStr

class htmlUtils:

    headers = {'User-Agent': UserAgent().random}
    url_data = {}
    
    @classmethod
    def getPathSaveHtml(cls,url,type=None):
        rstr = r"[\/\\\:\*\?\"\<\>\|\.]"  #  '/ \ : * ? " < > |'
        try:
            file_url = re.sub(rstr, "", url)
        except:
            file_url = "error_cache"
        file_path = os.path.join(pathStr.base_html_cache,file_url)
        if type == "new":
            return file_path
        if os.path.exists(file_path):
            if type == "read":
                with open(file_path,"r",encoding="utf-8") as fs:
                    return fs.read()
            return file_path
        else:
            return None
        
    @classmethod
    def saveHtml(cls,url,data):
        file_path = cls.getPathSaveHtml(url,type="new")
        dir_name = os.path.dirname(file_path)
        if not os.path.exists(dir_name):
            os.makedirs(dir_name)
        with open(file_path,"w",encoding="utf-8") as fs:
            fs.write(str(data))
    
    @classmethod
    def remove_HtmlCache(cls,url):
        file_path = cls.getPathSaveHtml(url,type="new")
        if os.path.exists(file_path):
            try:
                os.remove(file_path)
                print("已删除")
            except:
                print()
    
    @classmethod
    def getHTML(cls, curl,type=None):
        retries = Retry(total=1,
                        backoff_factor=0.1,
                        status_forcelist=[ 500, 502, 503, 504 ])
        s = requests.Session()
        s.mount('http://', HTTPAdapter(max_retries=retries))
        s.mount('https://', HTTPAdapter(max_retries=retries))
        count = 1
        #数据为空则获取数据
        url_text = cls.getPathSaveHtml(curl,"read")
        if url_text != None:
            return html.fromstring(url_text)
        while url_text == None:
            if count <= 3:
                try:
                    print(f"请求地址：{curl}")
                    res = s.get(curl,stream=True, headers=cls.headers, timeout=180,allow_redirects=True)
                    if res.status_code != 200:
                        cls.remove_HtmlCache(curl)
                        return None
                    if type == "bytes":
                        url_text = res
                    if type == "json":
                        #url_text = res.json()
                        url_text = json.loads(res.text)
                        cls.saveHtml(curl,res.text)
                    if type == None:
                        url_text = html.fromstring(res.text)
                        cls.saveHtml(curl,res.text)
                except:
                    print(f'Retry! 第{count}次')
                    time.sleep(1)
                    traceback.print_exc()
                    count += 1
                    continue 
            else:
                ntfy.sendMsg(f"fail 请求失败：{curl}")
                exit()
                break
        return url_text
    
    @classmethod
    def getBytes(cls, url):
        return cls.getHTML(url,type="bytes")
    
    @classmethod
    def getJSON(cls,url):
        res = requests.get(url,headers=cls.headers, timeout=180)
        if res.status_code != 200:
            return None
        try:
            return json.loads(res.text)
        except:
            return None
            
    @classmethod
    def xpathData(cls,c_xpath,url=None,num=None,not_eq=None,update=False):
        if url == None:
            url = cls.temp_url
        else:
            cls.temp_url = url            
        result = []
        if update:
            html_cache_path = cls.getPathSaveHtml(url,"new")
            if os.path.exists(html_cache_path):
                try:
                    os.remove(html_cache_path)
                    ntfy.sendMsg(f"html_cache更新成功 {html_cache_path}")
                except:
                    ntfy.sendMsg(f"html_cache更新失败 {html_cache_path}")
        #获取html实体数据
        et = cls.getHTML(url)
        #比对数据
        count = 1
        xpaths = et.xpath(c_xpath)
        for x in xpaths:
            if x != not_eq:
                result.append(x)
                count +=1
        if num != None:
            try:
                result = result[num]
            except:
                result = None
        return result