def check(self):
config = self.setConfig()
aheaders = {'Host':'m.twfanti.com'}
#aparams = { 'sort':'desc'}
CW = self.Sec['check word']
if not crab.Config.has_section(self.secName) :
self.logging ('\t未定義 {} Config\r\n'.format (self.secName))
return 2
#if len(self.Sec['keyword']) > 20:
url = self.Sec['Href']
#--end if
try :
res = MYSITE (url , headers = aheaders)
tempD = res.soup.select('span')[1]
chkD = str(tempD.text.strip())
if chkD == CW :
self.logging('\t{0} {1} 未有更新\n'.format(self.Sec['Name'],chkD))
return 0
else :
msg = '{0} 發佈更新 {1}\n'.format(self.Sec['Name'],chkD)
A = Book1(config)
A.getChapters()
bkhref = config['bsurl']+config['sUrl'].format(str(config['startChptr']))
self.notify('{0} 發佈更新 [{1}]({2})\n#小說更新 #{3}\n'.format(self.Sec['Name'],chkD, bkhref , config['title']))
self.logging('\t{}'.format(msg))
self.Sec['check word'] = chkD
self.Sec['Last Update'] = self.chk_date
except Exception as e:
print (e)
self.logging (str(e))
self.logging ('\t{}網站連結失敗\r\n'.format(self.secName))
finally :
pass
def check(self):
if not crab.Config.has_section(self.secName):
self.logging('\t未定義 {} Config\r\n'.format(self.secName))
return 2
url = 'http://{}/{}'.format(self.Sec['Site'], self.Sec['Page'])
status = self.Sec['Site Status']
try:
res = MYSITE(url)
tempD = res.soup.select(
self.Sec['Crab word'])[self.Sec.getint('Crab raw')]
chkD = tempD.text
self.Sec['Site Status'] = 'OK'
except:
self.logging('\t網站連結失敗\r\n')
self.Sec['Site Status'] = 'Error'
finally:
chkName = self.Sec['Name']
if self.Sec['Site Status'] == 'Error':
#若網站服務異常
# if status == 'OK' :
#若上次檢查時是好的
msgtxt = '{}網站服務異常'.format(self.secName)
self.logging('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
del res
return 1
else:
#網站服務正常
if status == 'Error':
#若上次檢查時是異常
msgtxt = '{}網站服務恢復'.format(self.secName)
#列印日誌
self.logging('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
#找 <fieldset>
uri = self.Sec['Last Uri']
DD = chkD
keyVal = self.Sec['check word']
LastUpdate = self.Sec['Last Update']
if keyVal == DD:
#無更新
pass
else:
#有更新
# 取得連結
msgtxt = '{}{}已更新'.format(chkName, DD)
self.logging('\t{}\r\n'.format(msgtxt))
self.Sec['check word'] = DD
self.Sec['Last Update'] = self.chk_date
self.notify(msgtxt)
del res
return 0
def check(self):
aheaders = {
'Cookie':
'__cfduid=daf56fbfbdd23f35e5d37891a102af8c11548041550; Hm_lvt_dfa59ae97c988b755b7dfc45bbf122ae=1569204591,1569206478; ftwwwacgsoucom=1; Hm_lpvt_dfa59ae97c988b755b7dfc45bbf122ae=1569206486',
'Host': 'www.36dm.club',
'Upgrade-Insecure-Requests': '1'
}
aparams = {
'bound': 'content',
'local': '1',
'keyword': '',
'sort_id': '0',
'field': 'title',
'node_id': '0',
'external': 'google'
}
CW = 'table#listTable tr.alt1 td'
url = 'https://www.36dm.club/'
if not crab.Config.has_section(self.secName):
self.logging('\t未定義 {} Config\r\n'.format(self.secName))
return 2
#if len(self.Sec['keyword']) > 20:
url = url + 'search.php'
aparams.clear()
sleep(15)
#--end if
aparams['keyword'] = self.Sec['keyword']
Last_Update = self.Sec['Last Update']
try:
res = MYSITE(url, headers=aheaders, params=aparams)
tempD = res.soup.select(CW)[0]
chkD = str(tempD.text)
if chkD == Last_Update:
self.logging('\t自{0}後，{1} 未有更新\n'.format(
chkD, self.Sec['Name']))
return 0
else:
msg = '{0} 於 {1} 發佈更新\n'.format(self.Sec['Name'], chkD)
self.Sec['Last Update'] = chkD
self.notify(msg + '\n#影片發佈\n')
self.logging('\t{}'.format(msg))
except Exception as e:
self.logging('\t{}網站連結失敗\r\n'.format(self.secName))
finally:
pass
def check(self):
if not crab.Config.has_section(self.secName):
self.logging('\t未定義 {} Config\r\n'.format(self.secName))
return 2
url = 'http://{}/{}'.format(self.Sec['Site'], self.Sec['Page'])
url_ = 'http://{}/vidlist/{}'.format(
self.Sec['Site'], self.Sec['Page'].split('btdy/dy')[1])
status = self.Sec['Site Status']
try:
res = MYSITE(url)
tempD = res.soup.select(
self.Sec['Crab word'])[self.Sec.getint('Crab raw')]
chkD = tempD.text
self.Sec['Site Status'] = 'OK'
except:
self.logging('\t網站連結失敗\r\n')
self.Sec['Site Status'] = 'Error'
finally:
chkName = self.Sec['Name']
if self.Sec['Site Status'] == 'Error':
#若網站服務異常
# if status == 'OK' :
#若上次檢查時是好的
msgtxt = '{}網站服務異常'.format(self.secName)
self.logging('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
del res
return 1
else:
#網站服務正常
if status == 'Error':
#若上次檢查時是異常
msgtxt = '{}網站服務恢復'.format(self.secName)
#列印日誌
self.logging('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
#找 <fieldset>
uri = self.Sec['Last Uri']
DD = chkD
keyVal = self.Sec['check word']
LastUpdate = self.Sec['Last Update']
with MyDS() as MDS:
MDS.CONNECT(crab.dsm)
if keyVal == DD:
#無更新
if self.Sec['DL Status'] == 'downloading':
#上次仍在下載中
if MDS.SID != '':
#Download Station 己連上
crab.lock.acquire()
with HQCDB(crab.DBFile,
self.secName) as tempDB:
tasks = tempDB.GetNotFinished()
if tasks != []:
#處理未完成更新的工作
for task in tasks:
#取得工作的狀態
info = MDS.GetInfo(task[0])
if info['success']:
DL_status = info['data'][
'tasks'][0]['status']
#DL_title = info['data']['tasks'][0]['title']
DL_uri = info['data']['tasks'][
0]['additional']['detail'][
'uri']
if (task[1] != 'Down') and (
task[1] != DL_status):
#若狀態有變
#更新狀態
tempDB.Update([
task[0], DL_uri,
DL_status
])
else:
tempDB.UpdateStatus(
[task[0], 'Down'])
#重新取回所有工作狀態
tasks = tempDB.GetNotFinished()
if tasks == []:
#全部下載完成
self.Sec['DL Status'] = 'finished'
msgtxt = '{}{} 已下載完成'.format(
chkName, DD)
# self.notify (msgtxt)
for task in tempDB.GetTasks().keys():
tempDB.UpdateStatus([task, 'Down'])
MDS.Delete(task)
#列印日誌
msgtxt = ('\t{}\r\n'.format(msgtxt))
else:
#下載中
#列印日誌
msgtxt = (
'\t{}{} 還有{}個下載排程\r\n'.format(
chkName, DD, len(tasks)))
del tempDB
crab.lock.release()
self.logging(msgtxt)
else:
#無法連上Download Station
self.logging('\t無法連結 NAS\r\n')
else:
#上次已完成下載
#列印日誌
self.logging('\t自 {} 後，{} 沒有更新\r\n'.format(
LastUpdate, chkName + DD))
else:
#有更新
# 取得連結
Files = []
res.get(url_)
tempf = res.soup.select('div.p_list li span a.d1')
tempt = res.soup.select('div.p_list li a.ico_1')
for i in range(len(tempf)):
Files.append(
[tempf[i]['href'], tempt[i]['title'].strip()])
# for file in res.soup.select('div.p_list li span a.d1'):
# Files.append(file['href'])
if Files != []:
crab.lock.acquire()
with HQCDB(crab.DBFile, self.secName) as tempDB:
if keyVal == '':
tempDB.ClearDB()
tempcount = 0
for File in Files:
uri = File[0]
title = File[1].strip()
if not tempDB.IsExistFile(uri):
if MDS.AddTask(
uri=uri,
des=self.Sec['destination']):
tempcount += 1
temptask = MDS.List(
)['data']['tasks'][-1]
tempDB.AddFile([
uri, temptask['id'],
temptask['status'], title
])
if tempcount > 0:
msgtxt = '{}{}已新增 {} 個下載排程'.format(
chkName, DD, tempcount)
self.Sec['DL Status'] = 'downloading'
else:
msgtxt = '{}{}已更新，但無新增下載連結'.format(chkName, DD)
del tempDB
crab.lock.release()
self.logging('\t{}\r\n'.format(msgtxt))
self.Sec['check word'] = DD
self.Sec['Last Update'] = self.chk_date
self.Sec['Last Uri'] = uri
self.notify(msgtxt)
else:
msgtxt = '網頁服務異常'
del Files
del res
del MDS
return 0
def check (self):
if not crab.Config.has_section(self.secName) :
self.logging('\t未定義 {} Config\r\n'.format (self.secName))
return 2
hd= { 'Host': 'www.gscq.me'
,'Upgrade-Insecure-Requests' : '1'
,'Cookie' :'bbs_token=RVz5QEmUkfLAIfn8RPO4egxAtbgGslmQr0Kc0M17Uz1aLZtm; bbs_sid=s1lemcj23bsbhgg9tfbt705r92'
}
url = 'https://{}/{}'.format(self.Sec['Site'],self.Sec['Page'])
status = self.Sec['Site Status']
try :
with MYSITE (url,headers = hd) as res :
tempD = res.soup.select (self.Sec['Crab word'])[self.Sec.getint('Crab raw')]
chkD = str(tempD)
#找 <fieldset>
FileSets = res.soup.find_all ('fieldset')
self.headers = res.headers.copy()
uri = self.Sec['Last Uri']
self.Sec['Site Status'] = 'OK'
except :
self.logging ('\t網站連結失敗\r\n')
self.Sec['Site Status'] = 'Error'
finally :
chkName = self.Sec['Name']
if self.Sec['Site Status'] == 'Error' :
#若網站服務異常
# if status == 'OK' :
#若上次檢查時是好的
try :
msgtxt = '{}網站服務異常'.format(self.secName)
self.logging ('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
del res
except :
pass
finally :
return 1
else :
#網站服務正常
if status == 'Error':
#若上次檢查時是異常
msgtxt = '{}網站服務恢復'.format(self.secName)
#列印日誌
self.logging ('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
SLD = self.Sec['Section Left Delimiter']
SRD = self.Sec['Section Right Delimiter']
tempDD = chkD.split(SLD)[self.Sec.getint('check Section')]
DD = '{}{}{}'.format(SLD,tempDD.split(SRD)[0],SRD)
keyVal = self.Sec['check word']
LastUpdate = self.Sec['Last Update']
with MyDS() as MDS:
MDS.CONNECT(crab.dsm)
if keyVal == DD :
#無更新
if self.Sec['DL Status'] == 'downloading' :
#上次仍在下載中
if MDS.SID != '' :
#Download Station 己連上
crab.lock.acquire()
with HQCDB(crab.DBFile,self.secName) as tempDB:
tasks = tempDB.GetNotFinished()
if tasks != [] :
#處理未完成更新的工作
for task in tasks:
#取得工作的狀態
info = MDS.GetInfo(task[0])
if info['success'] :
DL_status = info['data']['tasks'][0]['status']
#DL_uri = info['data']['tasks'][0]['additional']['detail']['uri']
if (task[1] != 'Down') and (task[1] != DL_status) :
#若狀態有變
#更新狀態
tempDB.UpdateStatus([task[0],DL_status])
else :
tempDB.UpdateStatus([task[0],'Down'])
#重新取回所有工作狀態
tasks = tempDB.GetNotFinished()
if tasks == [] :
#全部下載完成
self.Sec['DL Status'] = 'finished'
msgtxt = '{}{} 已下載完成'.format (chkName,DD)
# self.notify (msgtxt)
for task in tempDB.GetTasks().keys():
tempDB.UpdateStatus ([task,'Down'])
MDS.Delete(task)
#列印日誌
msgtxt = ('\t{}\r\n'.format(msgtxt))
else :
#下載中
#列印日誌
msgtxt = ('\t{}{} 還有{}個下載排程\r\n'.format(chkName,DD,len(tasks)))
del tempDB
crab.lock.release()
self.logging (msgtxt)
else :
#無法連上Download Station
self.logging ('\t無法連結 NAS\r\n')
else :
#上次已完成下載
#列印日誌
self.logging ('\t自 {} 後，{} 沒有更新\r\n'.format(LastUpdate,chkName+DD))
else :
#有更新
if FileSets != [] :
# 取得HQC連結
FileSet = str(FileSets[0])
soupHref = BeautifulSoup(FileSet,'html.parser')
#挑出 <ul class='attachlist'> <li> <a>
Files = soupHref.select('ul.attachlist li a')
crab.lock.acquire()
try :
#用於計算新增多少個排程
tempcount = 0
with HQCDB(crab.DBFile,self.secName) as tempDB:
if keyVal == '' :
tempDB.ClearDB()
#處理每一條連結
for File in Files:
uri = 'https://{}/{}'.format(self.Sec['Site'],File['href'])
title = File.text.strip()
if not tempDB.IsExistFile(uri) :
#如果連結不存在於資料庫
#設定檔案名稱
if crab.plat_Linux :
torrentPath = '/volume1/{}/{}'.format(self.Sec['destination'],'Torrent')
if not os.path.exists(torrentPath) :
os.makedirs(torrentPath)
tfn = '{}/{}'.format(torrentPath,title)
fn = '{}/{}.{}'.format(torrentPath,'HQC',title.split('.')[-1])
else :
try :
torrentPath = '{}\\{}'.format(crab.Config['DEBUG']['Windows Work Path'],'Torrent')
except :
torrentPath = 'C:\\MyCoding\\D_Check\\Torrent'
if not os.path.exists(torrentPath) :
os.makedirs(torrentPath)
tfn = '{}\\{}'.format(torrentPath,title)
fn = '{}\\{}.{}'.format(torrentPath,'HQC',title.split('.')[-1])
#取得torrent連結
try :
res1 = requests.get(uri,headers = self.headers,verify = False ,timeout = 15)
#torrent 存檔
with open ( tfn,'wb') as ff :
ff.write (res1._content)
with open ( fn,'wb') as ff :
ff.write (res1._content)
except Exception as e :
print ('torrent get Exception:' ,e)
del ff
#將torrent 加入排程
if MDS.AddTask (file = fn ,des = self.Sec['destination']) :
tempcount += 1
temptask = MDS.List()['data']['tasks'][-1]
tempDB.AddFile ([uri,temptask['id'],temptask['status'],title])
msgtxt = '{}{}已新增 {} 個下載排程'.format (chkName,DD,tempcount)
del tempDB
except Exception as e :
print (e)
crab.lock.release()
self.logging ('\t{}\r\n'.format (msgtxt))
if tempcount > 0 :
self.Sec['check word'] = DD
self.Sec['Last Update'] = self.chk_date
self.Sec['Last Uri'] = uri
self.Sec['DL Status'] = 'downloading'
self.notify (msgtxt)
else :
msgtxt = '網頁服務異常'
return 0
def check(self):
'''
return 0 : 網站服務正常
return 1 : 網站服務異常
return 2 : Config 未設定
Config 參數如下
Site : 網站
Page : 網頁
Name : 名稱
Crab word : 解析字詞
check word : 檢測字詞
Last Update : 上次更新日期
Last Uri : 前次的下載網址
Generate TXT : 產生link文字檔
DL Path : 下載影片檔的路徑
'''
if not crab.Config.has_section(self.secName):
self.logging('\t未定義 {} Config\r\n'.format(self.secName))
return 2
res = MYSITE(self.url)
ep = res.soup.select('div.vodh span')[0].text
if self.Sec['keyword'] not in res.soup.select('div.vodh h2')[0].text:
self.logging("{}\t找不到資源\n".format(self.chk_date))
return 0
if ep == self.Sec['check word']:
self.logging("\t{},沒有更新\n".format(self.Sec['Name']))
return 0
_uris = [x['value'] for x in res.soup.select(self.Sec['Crab word'])]
'''
_uris = list (map(lambda x: x['value'] , res.soup.select(self.Sec['Crab word'])))
將元素(x)的特定值('value')輸出重新組成(map(express,iterator))新的列表(list())
* map()的輸出是疊代器(iterator)
'''
_indexNew = (_uris.index(self.Sec['Last Uri']) +
1) if self.Sec['Last Uri'] in _uris else 0
if _indexNew < (len(_uris)):
with DPLfile(self.Sec['destination']) as DPL:
def appendx(x):
crab.lock.acquire()
DPL.append(x)
_DPL = DPLfile(crab.Config['LOG']['OK Log File'].format(
self.chk_date.split('(')[0]))
_DPL.append(x)
del _DPL
crab.lock.release()
list(
map(
lambda x: appendx(x)
if not DPL.isexist(x) else DPL.bypass(),
_uris[_indexNew:]))
'''
如果檔案中不存在x連結(not DPL.isexist(x))就新增連結(DPL.append(x))，否則略過(DPL.bypass())
DPL.append(x) if not DPL.isexist(x) else DPL.bypass()
* lambda 組成的函式，可以立刻輸入參數執行 (lambda : param1,param2.. : express(param1,param2..))(input1,input2..)
'''
if self.GenTXT:
DPL.toTXT()
self.GenTXT = 'no'
msg = '{},已增加連結'.format(self.Sec['Name'])
msgs = [
'[新連結{}]({})'.format(i + 1, x)
for (i, x) in enumerate(_uris[_indexNew:])
]
self.Sec['check word'] = ep
self.Sec['Last Update'] = self.chk_date
self.Sec['Last Uri'] = _uris[-1]
self.logging('\t' + msg + '\n')
self.notify(msg)
[self.notify(x) for x in msgs] if self.ShowLink else None
if 'DL Path' in [x for x in self.Sec.keys()]:
#if crab.Config.has_option(self.secName,'DL Path'):
if self.Sec['DL Path'] != '':
with MyDS() as MDS:
MDS.CONNECT(crab.dsm)
[
MDS.AddTask(uri=x, des=self.Sec['DL Path'])
for x in _uris[_indexNew:]
]
else:
self.logging("\t{}沒有更新\n".format(self.Sec['Name']))
return 0
def check(self):
'''
return 0 : 網站服務正常
return 1 : 網站服務異常
return 2 : Config 未設定
Config 參數如下
Site : 網站
Page : 網頁
Name : 名稱
Crab word : 解析字詞
Crab raw : 解析欄位 (table 使用;否則為 0)
Section Left Delimiter : 左邊界字元
Section Right Delimiter : 右邊界字元
check Section : 檢核區塊
check word : 檢測字詞
Last Update : 上次更新日期
Site Status : 上次檢測狀態
Last Uri : 前次的下載網址
DL ID : 下載工作ID
DL Status : 下載狀態
'''
aheaders = {
'Cookie':
'__cfduid=daf56fbfbdd23f35e5d37891a102af8c11548041550; Hm_lvt_dfa59ae97c988b755b7dfc45bbf122ae=1569204591,1569206478; ftwwwacgsoucom=1; Hm_lpvt_dfa59ae97c988b755b7dfc45bbf122ae=1569206486',
'Host': 'www.36dm.club',
'Upgrade-Insecure-Requests': '1'
}
aparams = {
'bound': 'content',
'local': '1',
'keyword': '',
'sort_id': '0',
'field': 'title',
'node_id': '0',
'external': 'google'
}
if not crab.Config.has_section(self.secName):
self.logging('\t未定義 {} Config\r\n'.format(self.secName))
return 2
# url = Config.get (secName,'Url')
urla = 'https://{}/'.format(self.Sec['Site'])
#if len(self.Sec['keyword']) >20 :
urla = urla + 'search.php'
aparams.clear()
sleep(15)
#---end if
aparams['keyword'] = self.Sec['keyword']
status = self.Sec['Site Status']
try:
res = MYSITE(urla, headers=aheaders, params=aparams)
# res.get(urla,headers = self.headers ,params = self.params)
tempD = res.soup.select(
self.Sec['Crab word'])[self.Sec.getint('Crab raw')]
chkD = str(tempD.text)
uri = self.Sec['Last Uri']
self.Sec['Site Status'] = 'OK'
except Exception as e:
self.logging('\t{}網站連結失敗\r\n'.format(self.secName))
self.Sec['Site Status'] = 'Error'
finally:
chkName = self.Sec['Name']
if self.Sec['Site Status'] == 'Error':
#若網站服務異常
# if status == 'OK' :
#若上次檢查時是好的
msgtxt = '{}網站服務異常'.format(self.secName)
self.logging('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
del res
return 1
else:
#網站服務正常
if status == 'Error':
#若上次檢查時是異常
msgtxt = '{}網站服務恢復'.format(self.secName)
#列印日誌
self.logging('\t{}\r\n'.format(msgtxt))
# self.notify (msgtxt)
SLD = self.Sec['Section Left Delimiter']
SRD = self.Sec['Section Right Delimiter']
tempDD = chkD.split(SLD)[self.Sec.getint('check Section')]
DD = '{}{}{}'.format(SLD, tempDD.split(SRD)[0], SRD)
keyVal = self.Sec['check word']
LastUpdate = self.Sec['Last Update']
with MyDS() as MDS:
MDS.CONNECT(crab.dsm)
if keyVal == DD:
#無更新
if self.Sec['DL Status'] == 'downloading':
#上次仍在下載中
if MDS.SID != '':
#Download Station 己連上
TK_id = self.Sec['DL ID']
DL_Info = MDS.GetInfo(TK_id)
if DL_Info['success'] == True:
#找到任務
if DL_Info['data']['tasks'][0][
'status'] == 'finished':
#下載完成
TK_Info = DL_Info['data']['tasks'][0]
TK_status = TK_Info['status']
TK_title = TK_Info['title'].strip()
TK_uri = TK_Info['additional'][
'detail']['uri']
crab.lock.acquire()
with HQCDB(crab.DBFile,
self.secName) as tempDB:
if tempDB.IsExistTask(TK_id):
tempDB.Update([
TK_id, TK_uri, TK_status,
TK_title
])
# tempDB.DelTask(TK_id)
del tempDB
crab.lock.release()
del TK_Info
msgtxt = '{}{} 已下載完成'.format(
chkName, DD)
MDS.Delete(self.Sec['DL ID'])
self.Sec['DL ID'] = ''
self.Sec['DL Status'] = 'finished'
# self.notify (msgtxt)
#列印日誌
self.logging('\t{}\r\n'.format(msgtxt))
else:
#下載中
#列印日誌
self.logging('\t{}{} 下載中\r\n'.format(
chkName, DD))
else:
#找不到任務
crab.lock.acquire()
with HQCDB(crab.DBFile,
self.secName) as tempDB:
if tempDB.IsExistTask(TK_id):
tempDB.DelTask(TK_id)
del tempDB
crab.lock.release()
self.Sec['DL ID'] = ''
self.Sec['DL Status'] = ''
self.logging(
'\t{}{} NAS 任務已被手動移除\r\n'.format(
chkName, DD))
del DL_Info
else:
#無法連上Download Station
self.logging('\t無法連結 NAS\r\n')
else:
#上次已完成下載
#列印日誌
self.logging('\t自 {} 後，{} 沒有更新\r\n'.format(
LastUpdate, chkName + DD))
else:
#有更新
#取得ACG資料磁力鏈結
try:
title = chkD.strip() + '.torrent'
res.get('http://{}/{}'.format(
self.Sec['Site'], tempD['href']))
#挑出 <a id='magnet'>
uri = res.soup.select('a#magnet')[0]['href']
tUri = res.soup.select('a#download')[0]['href']
torrentURI = 'http://{}/{}'.format(
self.Sec['Site'], tUri)
if crab.plat_Linux:
torrentPath = '/volume1/{}/{}'.format(
self.Sec['destination'], 'Torrent')
if not os.path.exists(torrentPath):
os.makedirs(torrentPath)
tfn = '{}/{}'.format(torrentPath, title)
fn = '{}/{}.{}'.format(torrentPath, 'HQC',
title.split('.')[-1])
else:
try:
torrentPath = '{}\\{}'.format(
crab.Config['DEBUG']
['Windows Work Path'], 'Torrent')
except:
torrentPath = 'C:\\MyCoding\\D_Check\\Torrent'
if not os.path.exists(torrentPath):
os.makedirs(torrentPath)
tfn = '{}\\{}'.format(torrentPath, title)
fn = '{}\\{}.{}'.format(
torrentPath, 'HQC',
title.split('.')[-1])
#取得torrent連結
try:
res1 = requests.get(torrentURI,
headers=aheaders,
timeout=15)
#torrent 存檔
with open(tfn, 'wb') as ff:
ff.write(res1._content)
with open(fn, 'wb') as ff:
ff.write(res1._content)
except Exception as e:
print('torrent get Exception:', e)
del ff
except:
self.logging('\t{}無法取得磁力鏈結\r\n'.format(
self.secName))
self.Sec['check word'] = DD
self.Sec['Last Update'] = self.chk_date
msgtxt = '{}{} 發佈'.format(chkName, DD)
if (uri != self.Sec['Last Uri']) and (
MDS.SID != '') and (uri != ''):
##Download Station 己連上 且 有新的連結
if MDS.AddTask(
uri=uri,
des=self.Sec['destination']) == True:
#成功加入 Download List
msgtxt = '{},已加入下載排程'.format(msgtxt)
TK_Info = MDS.List()['data']['tasks'][-1]
TK_status = TK_Info['status']
TK_id = TK_Info['id']
TK_title = tempD.text.strip()
TK_uri = TK_Info['additional']['detail']['uri']
crab.lock.acquire()
with HQCDB(crab.DBFile,
self.secName) as tempDB:
tempDB.AddFile(
[TK_uri, TK_id, TK_status, TK_title])
del tempDB
crab.lock.release()
del TK_Info
self.Sec['Last Uri'] = uri
self.Sec['DL ID'] = MDS.List(
)['data']['tasks'][-1]['id']
self.Sec['DL Status'] = 'downloading'
self.notify(msgtxt + '\n#影片發佈')
#列印日誌
self.logging('\t{}\r\n'.format(msgtxt))
del res
return 0
def check(self):
'''
return 0 : 程式正常完成
return 1 : 網站服務異常
return 2 : Config 未設定
Config 參數如下
Url : 爬取網址
update date : 資料更新日期
version : 資料版本
S_Link : 轉址位址
Site Status : 上次檢測時網站狀態
'''
if not crab.Config.has_section(self.secName):
self.logging ('\t未定義 {} Config\r\n'.format (self.secName))
return 2
temp_hd = {\
'Accept':'text/html,application/xhtml;q=0.9,image/webp,*/*;q=0.8' , \
'Accept-Encoding':'gzip, deflate' ,\
'Accept-Language':'zh-TW,zh;q=0.8,en-US;q=0.5,en;q=0.3' ,\
'Connection':'keep-alive' ,\
'Cookie':'ASPSESSIONIDSCQSTABC=LIFMIBDAKCPBIMNMLEMMPHHB' ,\
"Host":'www.ucppweb.com' ,\
'Upgrade-Insecure-Requests':'1' ,\
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; ) Gecko/20100101 Firefox/65.0' \
}
#===============程式起始==============================================
status = self.Sec['Site Status']
try :
with MYSITE (self.Sec['Url']) as DD :
ver = DD.soup.select('table#ProceM1_dalist1_ctl00_dalist2 tr td tr td')[1].text
# update_date = DD.soup.select('table#ProceM1_dalist1_ctl00_dalist2 tr td tr td')[3].text
tempURL = DD.soup.select('table#ProceM1_dalist1_ctl00_dalist2 tr td tr td a')[0]['href']
with requests.get (tempURL , headers = temp_hd , allow_redirects = False ,timeout = 10 ) as temp_res:
S_Link = str (temp_res.headers['Location'])
self.Sec['Site Status'] = 'OK'
except :
self.Sec['Site Status'] = 'Error'
finally :
if self.Sec['Site Status'] == 'Error' :
self.logging ('\t{}網站服務異常\r\n'.format (self.secName))
if status == 'OK' :
self.notify ('{} 網站服務異常'.format(self.secName))
return 1
else :
if status == 'Error':
self.logging ('\t{}網站服務恢復\r\n'.format (self.secName))
self.notify ('{} 網站服務恢復'.format(self.secName))
DocName = ver
update_in_DB = self.Sec['update date']
Doc_in_DB = self.Sec['version']
link_in_DB = self.Sec['S_Link']
if S_Link == link_in_DB :
self.logging ('\t自 {} 後，大D沒有更新\r\n'.format (update_in_DB))
else :
if Doc_in_DB == DocName :
tempDoc = '子版大D'
else :
tempDoc = DocName
self.Sec['update date'] = self.chk_date
self.Sec['version'] = DocName
self.Sec['S_Link'] = S_Link
msgtxt = '{} 發佈'.format (tempDoc)
self.logging ('\t{}\r\n'.format(msgtxt))
self.notify (msgtxt)
return 0