| r39 vs r37 | ||
|---|---|---|
| 1 | api_url, wiki_url, discuss_doc, discuss_doc = selctwiki() | |
| 2 | 1 | |
| 3 | headers = {'Content-Type': 'application/json', 'Authorization': 'Bearer {}'.format(APItoken)} | |
| 4 | discuss_headers = {'User-Agent': 'Mozilla/5.0'} | |
| 5 | #### | |
| 6 | sys_stop=False | |
| 7 | 2 | |
| 8 | logger = logging.getLogger("wiki edit") | |
| 9 | discusslogger = logging.getLogger("discuss HTML") | |
| 10 | streamlogger = logging.getLogger("log stream") | |
| 11 | ||
| 12 | logging.addLevelName(11, "edit History") | |
| 13 | logging.editHistory = 11 | |
| 14 | ||
| 15 | logging.addLevelName(31, "edit Fail") | |
| 16 | logging.editFail= 31 | |
| 17 | ||
| 18 | logging.addLevelName(41, "edit Error") | |
| 19 | logging.editError = 41 | |
| 20 | ||
| 21 | logging.addLevelName(35, "working Emergency Stop") | |
| 22 | logging.workingEmergencyStop = 35 | |
| 23 | ||
| 24 | logging.addLevelName(25, "discuss Error") | |
| 25 | logging.discussError = 25 | |
| 26 | ||
| 27 | logging.addLevelName(12, "discuss Load") | |
| 28 | logging.discussLoad = 12 | |
| 29 | ||
| 30 | logger.setLevel(logging.DEBUG) | |
| 31 | discusslogger.setLevel(logging.INFO) | |
| 32 | ||
| 33 | formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s') | |
| 34 | stream_hander = logging.StreamHandler() | |
| 35 | stream_hander.setFormatter(formatter) | |
| 36 | streamlogger.addHandler(stream_hander) | |
| 37 | progStart_day=str(time.strftime('%Y %m %d', time.localtime())) | |
| 38 | progStart_time=str(time.strftime('%H %M %S', time.localtime())) | |
| 39 | ||
| 40 | if not os.path.exists('/content/drive/My Drive/Colab Notebooks/logs/{}'.format(progStart_day)): | |
| 41 | os.makedirs('/content/drive/My Drive/Colab Notebooks/logs/{}'.format(progStart_day)) | |
| 42 | os.makedirs('/content/drive/My Drive/Colab Notebooks/logs/{}/{}'.format(progStart_day,progStart_time)) | |
| 43 | ||
| 44 | file_handler = logging.FileHandler('/content/drive/My Drive/Colab Notebooks/logs/{}/{}/wiki edit.log'.format(progStart_day,progStart_time)) | |
| 45 | file_handler.setFormatter(formatter) | |
| 46 | logger.addHandler(file_handler) | |
| 47 | ||
| 48 | discuss_file_handler = logging.FileHandler('/content/drive/My Drive/Colab Notebooks/logs/{}/{}/discuss HTML.log'.format(progStart_day,progStart_time)) | |
| 49 | discuss_file_handler.setFormatter(formatter) | |
| 50 | discusslogger.addHandler(discuss_file_handler) | |
| 51 | ||
| 52 | error_file_handler = logging.FileHandler('/content/drive/My Drive/Colab Notebooks/logs/{}/{}/error.log'.format(progStart_day,progStart_time)) | |
| 53 | error_file_handler.setFormatter(formatter) | |
| 54 | streamlogger.addHandler(error_file_handler) | |
| 55 | ||
| 56 | class checkWikiThread(): | |
| 57 | async def alterResponseTry(self,response,wait_time=0.2): | |
| 58 | try: | |
| 59 | await response.html.arender(wait=wait_time) | |
| 60 | html = await response.html.html | |
| 61 | loadComple = re.search("토론",str(html)) | |
| 62 | if loadComple==None: | |
| 63 | logger.log(logging.discussLoad, ('not Loding, wait_time: {}'.format(wait_time))) | |
| 64 | print('not Loding, wait_time:',wait_time) | |
| 65 | if wait_time>40: | |
| 66 | discusslogger.log(logging.discussError,(html)) | |
| 67 | logger.log(logging.discussError, ("timeout, html log saved: {} discuss HTML.log".format(str(progStart_time)))) | |
| 68 | streamlogger.log(logging.discussError, ("timeout, html log saved: {} discuss HTML.log".format(str(progStart_time)))) | |
| 69 | html= await self.alterResponseTry(response,wait_time=float(wait_time+10)) | |
| 70 | else : | |
| 71 | logger.log(logging.discussLoad, 'load comple') | |
| 72 | return html | |
| 73 | except Exception as ex: | |
| 74 | logger.log(logging.discussError, ex) | |
| 75 | streamlogger.log(logging.discussError, ex) | |
| 76 | html= await self.alterResponseTry(response,wait_time) | |
| 77 | return html | |
| 78 | def __init__(self): | |
| 79 | self.state=False | |
| 80 | self.discuss_state = None | |
| 81 | async def run(self): | |
| 82 | self.state=True | |
| 83 | response = await requests.get("https://{}/discuss/{}".format(wiki_url,discuss_doc),headers=discuss_headers, timeout=100) | |
| 84 | html = response.text | |
| 85 | loadComple = re.search("토론",str(html)) | |
| 86 | if loadComple==None: | |
| 87 | logger.log(logging.discussLoad, 'not Loding, alter way start') | |
| 88 | #print(html) | |
| 89 | asession = await AsyncHTMLSession() | |
| 90 | response = await asession.get("https://{}/discuss/{}".format(wiki_url,discuss_doc),headers=discuss_headers) | |
| 91 | html= await self.alterResponseTry(response) | |
| 92 | self.discuss_state = re.search("\/discuss\/[\w,%,:]*#s-1",str(html)) | |
| 93 | time.sleep(30) | |
| 94 | self.state = False | |
| 95 | ||
| 96 | def linkcheckchange(match_obj): | |
| 97 | #구버전 기본값 | |
| 98 | #print(match_obj) | |
| 99 | #print(match_obj[0]) | |
| 100 | #link = match_obj.group('link') | |
| 101 | #anchor = match_obj.group('anchor') | |
| 102 | #content = match_obj.group('content') | |
| 103 | #namebar = match_obj.group('namebar') | |
| 104 | #for target,replace in targets: | |
| 105 | #if link==target: | |
| 106 | #if content==None: | |
| 107 | #내용이 없을경우 원래 링크가 내용이 됨 | |
| 108 | #content=link | |
| 109 | #link=replace | |
| 110 | #if anchor==None: | |
| 111 | #anchor='' | |
| 112 | #if namebar==None: | |
| 113 | #namebar='' | |
| 114 | #return '[[{}{}{}|{}]]'.format(namebar,link,anchor,content) | |
| 115 | # | |
| 116 | #[[]] 전용 | |
| 117 | first = match_obj.group('first') | |
| 118 | link = match_obj.group('link') | |
| 119 | middle = match_obj.group('middle') | |
| 120 | detachBar = match_obj.group('detachBar') | |
| 121 | content = match_obj.group('content') | |
| 122 | last = match_obj.group('last') | |
| 123 | anchor = match_obj.group('anchor') | |
| 124 | if middle==None: | |
| 125 | middle='' | |
| 126 | for target in targets: | |
| 127 | target_doc=target['document'] | |
| 128 | replace=target['replace'] | |
| 129 | if link==target_doc: | |
| 130 | #내용이 없을경우 원래 링크가 내용이 됨 | |
| 131 | #content_replace bool 추가 | |
| 132 | if content==None and content_replace: | |
| 133 | #혹시 모를 사고 예방 | |
| 134 | if detachBar==None: | |
| 135 | content='|{}'.format(link) | |
| 136 | else: | |
| 137 | content='{}'.format(link) | |
| 138 | elif content==None: | |
| 139 | content='' | |
| 140 | link=replace | |
| 141 | return '{}{}{}{}{}'.format(first,link,middle,content,last) | |
| 142 | return match_obj.group(0) | |
| 143 | def checkchange(match_obj): | |
| 144 | #[[]] 제외 기본 변경 | |
| 145 | first = match_obj.group('first') | |
| 146 | link = match_obj.group('link') | |
| 147 | last = match_obj.group('last') | |
| 148 | for target in targets: | |
| 149 | target_doc=target['document'] | |
| 150 | replace=target['replace'] | |
| 151 | if link==target_doc: | |
| 152 | link=replace | |
| 153 | #print('hidden') | |
| 154 | return '{}{}{}'.format(first,link,last) | |
| 155 | return match_obj.group(0) | |
| 156 | def checkdelete(match_obj): | |
| 157 | #분류 정리 전용 | |
| 158 | link = match_obj.group('link') | |
| 159 | anchor = match_obj.group('anchor') | |
| 160 | content = match_obj.group('content') | |
| 161 | for target in targets: | |
| 162 | target_doc=target['document'] | |
| 163 | replace=target['replace'] | |
| 164 | if link==target_doc: | |
| 165 | if content==None: | |
| 166 | #내용이 없을경우 원래 링크가 내용이 됨 | |
| 167 | content=link | |
| 168 | link=replace | |
| 169 | if anchor==None: | |
| 170 | anchor='' | |
| 171 | return '' | |
| 172 | return match_obj.group(0) | |
| 173 | ||
| 174 | def edit_link(title, text): | |
| 175 | link_patten=re.compile(r"(?P<first>\[\[(?P<namebar>(:)?))(?P<link>((\\\\)|(\\\#)|(\\\|)|(\\\[)|(\\\])|[^\[\]#|])*)(?P<middle>(?P<anchor>#((\\\\)|(\\\#)|(\\\|)|(\\\[)|(\\\])|[^\[\]#|])*)?(?P<detachBar>\|)?)(?(detachBar)(?P<content>((\\\\)|(\\\#)|(\\\|)|(\\\[)|(\\\])|[^\[\]|])*))(?P<last>\]\])") | |
| 176 | otherMean_patten=re.compile(r"(?P<first>rd\d=)(?P<link>((\\\,)|(\\\\)|(\\\))|[^\,)])*)(?P<last>[,)])") | |
| 177 | detailContent_patten=re.compile(r"(?P<first>문서명=)(?P<link>((\\\,)|(\\\\)|(\\\))|[^\,)])*)(?P<last>[,)])") | |
| 178 | categoryMean_patten=re.compile(r"(?P<first>n\d=)(?P<link>((\\\,)|(\\\\)|(\\\))|[^\,)])*)(?P<last>[,)])") | |
| 179 | top_patten=re.compile(r"(?P<first>top\d=)(?P<link>((\\\,)|(\\\\)|(\\\))|[^\,)])*)(?P<last>[,)])") | |
| 180 | include_patten=re.compile(r"(?P<first>\[include\()(?P<link>((\\\,)|(\\\\)|(\\\))|[^\,)])*)(?P<last>((?P<comma>,)?)?(?(comma)((\\\,)|(\\\\)|(\\\))|[^)])*)\)\])") | |
| 181 | redirect_patten=re.compile(r"(?P<first>#redirect )(?P<link>((\\\\)|(\\\#)|(\\\|)|(\\\[)|(\\\])|[^\[\]#|])*)(?P<last>(?P<anchor>#)?.*\n)") | |
| 182 | ||
| 183 | normal_new_text=link_patten.sub(linkcheckchange,text) | |
| 184 | new_text=otherMean_patten.sub(checkchange,normal_new_text) | |
| 185 | new_text=detailContent_patten.sub(checkchange,new_text) | |
| 186 | new_text=categoryMean_patten.sub(checkchange,new_text) | |
| 187 | new_text=top_patten.sub(checkchange,new_text) | |
| 188 | new_text=include_patten.sub(checkchange,new_text) | |
| 189 | new_text=redirect_patten.sub(checkchange,new_text) | |
| 190 | if normal_new_text!=new_text: | |
| 191 | logger.log(logging.editHistory,('특수 변경 문서명: {}'.format(title))) | |
| 192 | return new_text | |
| 193 | ||
| 194 | def backlinkchange(): | |
| 195 | data={} | |
| 196 | data['edit']=[] | |
| 197 | for target in targets: | |
| 198 | target_doc=target['document'] | |
| 199 | replace=target['replace'] | |
| 200 | target_backlinks = [] | |
| 201 | backlink_value = '' | |
| 202 | namespaces=[] | |
| 203 | res = requests.get('https://{}/api/backlink/{}'.format(api_url,target_doc), headers = headers).json() | |
| 204 | for namespace in res['namespaces']: | |
| 205 | namespaces.append(namespace['namespace']) | |
| 206 | if len(black_namespaces)>0: #블랙 네임이 있다면 | |
| 207 | for black_namespace in black_namespaces: | |
| 208 | if black_namespace in namespaces: | |
| 209 | namespaces.remove(black_namespace) | |
| 210 | if len(namespaces)>0: | |
| 211 | target_namespace = namespaces.pop(0) | |
| 212 | else: | |
| 213 | target_namespace = None | |
| 214 | while target_namespace != None: | |
| 215 | res = requests.get('https://{}/api/backlink/{}?namespace={}&from={}'.format(api_url,target_doc,target_namespace, backlink_value), headers = headers).json() | |
| 216 | backlinks=res['backlinks'] | |
| 217 | backlink_value=res['from'] | |
| 218 | for doc in backlinks: | |
| 219 | white=False | |
| 220 | for white_doc in nontargets: | |
| 221 | if doc['document'] == white_doc: | |
| 222 | logger.info("화이트 리스트 문서 '{}' Pass".format(doc['document'])) | |
| 223 | white=True | |
| 224 | break | |
| 225 | if white: | |
| 226 | continue | |
| 227 | target_backlinks.append(doc['document']) | |
| 228 | if backlink_value==None: | |
| 229 | if len(namespaces)>0: | |
| 230 | target_namespace = namespaces.pop(0) | |
| 231 | backlink_value='' | |
| 232 | else: | |
| 233 | break | |
| 234 | for doc in target_backlinks: | |
| 235 | try: | |
| 236 | res = requests.get('https://{}/api/edit/{}'.format(api_url,doc), headers = headers).json() | |
| 237 | except: | |
| 238 | res = requests.get('https://{}/api/edit/{}'.format(api_url,doc), headers = headers) | |
| 239 | logger.log(logging.workingEmergencyStop, str(res.text)) | |
| 240 | streamlogger.log(logging.workingEmergencyStop, str(res.text)) | |
| 241 | exit() | |
| 242 | try: | |
| 243 | if not res['exists']: | |
| 244 | continue | |
| 245 | except: | |
| 246 | logger.log(logging.editFail, ('문서명: {}'.format(doc),'res: {}'.format(res))) | |
| 247 | streamlogger.log(logging.editFail, ('문서명: {}'.format(doc),'res: {}'.format(res))) | |
| 248 | continue | |
| 249 | ||
| 250 | token = res['token'] | |
| 251 | text = str(res['text']) | |
| 252 | new_text = edit_link(doc, text) | |
| 253 | res = requests.post('https://{}/api/edit/{}'.format(api_url,doc), json = {'text': new_text, 'log': log, 'token': token}, headers = headers) | |
| 254 | try: | |
| 255 | if res.json()['status'] != 'success': | |
| 256 | logger.log(logging.editError, ('문서명: {}'.format(doc),'res: {}'.format(res.text))) | |
| 257 | streamlogger.log(logging.editError, ('문서명: {}'.format(doc),'res: {}'.format(res.text))) | |
| 258 | else: | |
| 259 | data['edit'].append({ | |
| 260 | "doc": str(doc), | |
| 261 | "rev": res.json()['rev'], | |
| 262 | "text":text | |
| 263 | }) | |
| 264 | logger.log(logging.editHistory,('문서명: {}'.format(doc),'rev: {}'.format(res.json()['rev']))) | |
| 265 | except Exception as ex: | |
| 266 | logger.critical(('문서명:',doc,'Error:',ex)) | |
| 267 | logger.log(logging.editError,(('문서명:',doc,'Error:',ex))) | |
| 268 | streamlogger.critical(('문서명:',doc,'Error:',ex)) | |
| 269 | time.sleep(1) | |
| 270 | with open('/content/drive/My Drive/Colab Notebooks/logs/{}/{}/edit_history.txt'.format(progStart_day,progStart_time), 'w') as outfile: | |
| 271 | json.dump(data, outfile, indent=4, ensure_ascii=False) | |
| 272 | ||
| 273 | def revert(): | |
| 274 | data={} | |
| 275 | data['edit']=[] | |
| 276 | json_data = {} | |
| 277 | with open('/content/drive/My Drive/Colab Notebooks/logs/{}/{}/edit_history.txt'.format(revert_day,revert_time), "r") as json_file: | |
| 278 | json_data = json.load(json_file) | |
| 279 | for target in json_data['edit']: | |
| 280 | doc = target['doc'] | |
| 281 | try: | |
| 282 | res = requests.get('https://{}/api/edit/{}'.format(api_url,doc), headers = headers).json() | |
| 283 | except: | |
| 284 | res = requests.get('https://{}/api/edit/{}'.format(api_url,doc), headers = headers) | |
| 285 | logger.log(logging.workingEmergencyStop, str(res.text)) | |
| 286 | streamlogger.log(logging.workingEmergencyStop, str(res.text)) | |
| 287 | exit() | |
| 288 | try: | |
| 289 | if not res['exists']: | |
| 290 | continue | |
| 291 | except: | |
| 292 | logger.log(logging.editFail, ('문서명: {}'.format(doc),'res: {}'.format(res))) | |
| 293 | streamlogger.log(logging.editFail, ('문서명: {}'.format(doc),'res: {}'.format(res))) | |
| 294 | continue | |
| 295 | ||
| 296 | token = res['token'] | |
| 297 | text = str(res['text']) | |
| 298 | new_text = target['text'] | |
| 299 | log=log+'(r{}으로 되돌림)'.format(str(int(target['rev'])-1)) | |
| 300 | ||
| 301 | res = requests.post('https://{}/api/edit/{}'.format(api_url,doc), json = {'text': new_text, 'log': log, 'token': token}, headers = headers) | |
| 302 | if res.json()['status'] != 'success': | |
| 303 | logger.log(logging.editError, ('문서명: {}'.format(doc),'res: {}'.format(res.text))) | |
| 304 | streamlogger.log(logging.editError, ('문서명: {}'.format(doc),'res: {}'.format(res.text))) | |
| 305 | else: | |
| 306 | data['edit'].append({ | |
| 307 | "doc": str(doc), | |
| 308 | "rev": res.json()['rev'], | |
| 309 | "text":text | |
| 310 | }) | |
| 311 | logger.log(logging.editHistory,('문서명: {}'.format(doc),'rev: {}'.format(res.json()['rev']))) | |
| 312 | ||
| 313 | time.sleep(1) | |
| 314 | with open('/content/drive/My Drive/Colab Notebooks/logs/{}/{}/edit_history.txt'.format(progStart_day,progStart_time), 'w') as outfile: | |
| 315 | json.dump(data, outfile, indent=4, ensure_ascii=False) | |
| 316 | ||
| 317 | def customlinkchange(): | |
| 318 | data={} | |
| 319 | data['edit']=[] | |
| 320 | json_data = {} | |
| 321 | for target, replace in targets: | |
| 322 | for doc in custom_list: | |
| 323 | try: | |
| 324 | res = requests.get('https://{}/api/edit/{}'.format(api_url,doc), headers = headers).json() | |
| 325 | except: | |
| 326 | res = requests.get('https://{}/api/edit/{}'.format(api_url,doc), headers = headers) | |
| 327 | logger.log(logging.workingEmergencyStop, str(res.text)) | |
| 328 | streamlogger.log(logging.workingEmergencyStop, str(res.text)) | |
| 329 | exit() | |
| 330 | try: | |
| 331 | if not res['exists']: | |
| 332 | continue | |
| 333 | except: | |
| 334 | logger.log(logging.editFail, ('문서명: {}'.format(doc),'res: {}'.format(res))) | |
| 335 | streamlogger.log(logging.editFail, ('문서명: {}'.format(doc),'res: {}'.format(res))) | |
| 336 | continue | |
| 337 | ||
| 338 | ||
| 339 | token = res['token'] | |
| 340 | text = str(res['text']) | |
| 341 | new_text = edit_link(doc, text) | |
| 342 | ||
| 343 | res = requests.post('https://{}/api/edit/{}'.format(api_url,doc), json = {'text': new_text, 'log': log, 'token': token}, headers = headers) | |
| 344 | if res.json()['status'] != 'success': | |
| 345 | logger.log(logging.editError, ('문서명: {}'.format(doc),'res: {}'.format(res.text))) | |
| 346 | streamlogger.log(logging.editError, ('문서명: {}'.format(doc),'res: {}'.format(res.text))) | |
| 347 | else: | |
| 348 | data['edit'].append({ | |
| 349 | "doc": str(doc), | |
| 350 | "rev": res.json()['rev'], | |
| 351 | "text":text | |
| 352 | }) | |
| 353 | logger.log(logging.editHistory,('문서명: {}'.format(doc),'rev: {}'.format(res.json()['rev']))) | |
| 354 | ||
| 355 | time.sleep(1) | |
| 356 | ||
| 357 | class runningThread(threading.Thread): | |
| 358 | def __init__(self): | |
| 359 | super().__init__() | |
| 360 | self.state=False | |
| 361 | def run(self): | |
| 362 | self.state=True | |
| 363 | logger.info('working start') | |
| 364 | print('working start') | |
| 365 | if mod=='normal': | |
| 366 | backlinkchange() | |
| 367 | elif mod=='revert': | |
| 368 | if revert_day != '' or revert_day != '': | |
| 369 | revert() | |
| 370 | else: | |
| 371 | print('revert 시간이 지정되지 않았습니다.') | |
| 372 | log = '자동 편집 중 ' | |
| 373 | print('로그 변경됨:'+log+'(r{}으로 되돌림)'.format('int')) | |
| 374 | elif mod=='custom': | |
| 375 | customlinkchange() | |
| 376 | else: | |
| 377 | print('mod not select') | |
| 378 | logger.info('working end') | |
| 379 | print('working end') | |
| 380 | self.state=False | |
| 381 | ||
| 382 | #### | |
| 383 | checkDiscuss=checkWikiThread() | |
| 384 | custom_thread=runningThread() | |
| 385 | custom_thread.start() | |
| 386 | while True: | |
| 387 | try: | |
| 388 | if not checkDiscuss.state: | |
| 389 | checkDiscuss.run() | |
| 390 | if not custom_thread.state or sys_stop: | |
| 391 | logger.info('System Stop') | |
| 392 | print('system stop') | |
| 393 | break | |
| 394 | if checkDiscuss.discuss_state != None: | |
| 395 | logger.log(logging.workingEmergencyStop, 'discuss normal, System Emergency Stop') | |
| 396 | streamlogger.log(logging.workingEmergencyStop, 'discuss normal, System Emergency Stop') | |
| 397 | break | |
| 398 | except Exception as ex: | |
| 399 | logger.critical(ex) | |
| 400 | streamlogger.critical(ex) | |
| 401 | break | |
| 402 | logging.shutdown() | |
| 403 | reload(logging) |