Guest User

Untitled

a guest
Jul 6th, 2021
104
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 26.37 KB | None | 0 0
  1.  
  2. import asyncio
  3. import json
  4. import lxml.html
  5. from datetime import datetime, timedelta
  6. import itertools
  7. import aiohttp
  8. import filetype
  9.  
  10. DOCS_PER_PAGE = 200
  11.  
  12. GET_HEADERS = {
  13. "User-Agent": "Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/67.0.3396.87 Mobile Safari/537.36"
  14. }
  15. XML_HTTP_REQ_HEADERS = {
  16. "Accept": "*/*",
  17. "Connection": "keep-alive",
  18. "User-Agent": "Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/67.0.3396.87 Mobile Safari/537.36",
  19. "X-Requested-With": "XMLHttpRequest",
  20. "Accept-Encoding": "gzip, deflate, br",
  21. "Accept-Language": "en-US,en;q=0.5",
  22. "X-Requested-With": "XMLHttpRequest",
  23. "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
  24. }
  25.  
  26. POST_HEADERS = {
  27. "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
  28. "Accept-Encoding": "gzip, deflate, br",
  29. "Accept-Language": "en-US,en;q=0.9,ko;q=0.8",
  30. "Cache-Control": "no-cache",
  31. "Connection": "keep-alive",
  32. "Pragma": "no-cache",
  33. "Upgrade-Insecure-Requests": "1",
  34. "User-Agent": "Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/67.0.3396.87 Mobile Safari/537.36",
  35. }
  36.  
  37. GALLERY_POSTS_COOKIES = {
  38. "__gat_mobile_search": 1,
  39. "list_count": DOCS_PER_PAGE,
  40. }
  41.  
  42. import re
  43. def unquote(encoded):
  44. return re.sub(r'\\u([a-fA-F0-9]{4}|[a-fA-F0-9]{2})', lambda m: chr(int(m.group(1), 16)), encoded)
  45. def quote(decoded):
  46. arr = []
  47. for c in decoded:
  48. t = hex(ord(c))[2:].upper()
  49. if len(t) >= 4:
  50. arr.append("%u" + t)
  51. else:
  52. arr.append("%" + t)
  53. return "".join(arr)
  54. def peek(iterable):
  55. try:
  56. first = next(iterable)
  57. except StopIteration:
  58. return None
  59. return first, itertools.chain((first,), iterable)
  60.  
  61. class DocumentIndex:
  62. __slots__ = ["id", "subject", "title", "board_id", "has_image", "author", "time", "view_count", "comment_count", "voteup_count", "document", "comments"]
  63. def __init__(self, id, board_id, title, has_image, author, time, view_count, comment_count, voteup_count, document, comments, subject):
  64. self.id = id
  65. self.board_id = board_id
  66. self.title = title
  67. self.has_image = has_image
  68. self.author = author
  69. self.time = time
  70. self.view_count = view_count
  71. self.comment_count = comment_count
  72. self.voteup_count = voteup_count
  73. self.document = document
  74. self.comments = comments
  75. self.subject = subject
  76. def __str__(self):
  77. return f"{self.subject or ''}\t|{self.id}\t|{self.time.isoformat()}\t|{self.author}\t|{self.title}({self.comment_count}) +{self.voteup_count}"
  78.  
  79. class Document:
  80. __slots__ = ["id", "board_id", "title", "author", "author_id", "contents", "images", "html", "view_count", "voteup_count", "votedown_count", "logined_voteup_count", "time", "subject", "comments"]
  81. def __init__(self, id, board_id, title, author, author_id, contents, images, html, view_count, voteup_count, votedown_count, logined_voteup_count, time, comments, subject=None):
  82. self.id = id
  83. self.board_id = board_id
  84. self.title = title
  85. self.author = author
  86. self.author_id = author_id
  87. self.contents = contents
  88. self.images = images
  89. self.html = html
  90. self.view_count = view_count
  91. self.voteup_count = voteup_count
  92. self.votedown_count = votedown_count
  93. self.logined_voteup_count = logined_voteup_count
  94. self.comments = comments
  95. self.time = time
  96. self.subject = None
  97. def __str__(self):
  98. return f"{self.subject or ''}\t|{self.id}\t|{self.time.isoformat()}\t|{self.author}\t|{self.title}({self.comment_count}) +{self.voteup_count} -{self.votedown_count}\n{self.contents}"
  99.  
  100. class Comment:
  101. __slots__ = ["id", "parent_id", "author", "author_id", "contents", "dccon", "voice", "time"]
  102. def __init__(self, id, parent_id, author, author_id, contents, dccon, voice, time):
  103. self.id = id
  104. self.parent_id = parent_id
  105. self.author = author
  106. self.author_id = author_id
  107. self.contents = contents
  108. self.dccon = dccon
  109. self.voice = voice
  110. self.time = time
  111. def __str__(self):
  112. return f"ㄴ {self.author}: {self.contents or ''}{self.dccon or ''}{self.voice or ''} | {self.time}"
  113.  
  114. class Image:
  115. __slots__ = ["src", "document_id", "board_id", "session"]
  116. def __init__(self, src, document_id, board_id, session):
  117. self.src = src
  118. self.document_id = document_id
  119. self.board_id = board_id
  120. self.session = session
  121. async def load(self):
  122. headers = GET_HEADERS.copy()
  123. headers["Referer"] = "https://m.dcinside.com/board/{}/{}".format(self.board_id, self.document_id)
  124. async with self.session.get(self.src, cookies=GALLERY_POSTS_COOKIES, headers=headers) as res:
  125. return await res.read()
  126. async def download(self, path):
  127. headers = GET_HEADERS.copy()
  128. headers["Referer"] = "https://m.dcinside.com/board/{}/{}".format(self.board_id, self.document_id)
  129. async with self.session.get(self.src, cookies=GALLERY_POSTS_COOKIES, headers=headers) as res:
  130. bytes = await res.read()
  131. ext = filetype.guess(bytes).extension
  132. with open(path + '.' + ext, 'wb') as f:
  133. f.write(bytes)
  134.  
  135.  
  136.  
  137. class API:
  138. def __init__(self):
  139. self.session = aiohttp.ClientSession(headers=GET_HEADERS, cookies={"_ga": "GA1.2.693521455.1588839880"})
  140. async def close(self):
  141. await self.session.close()
  142. async def __aenter__(self):
  143. return self
  144. async def __aexit__(self, *args, **kwargs):
  145. await self.close()
  146. async def watch(self, board_id):
  147. pass
  148. async def board(self, board_id, num=-1, start_page=1, document_id_upper_limit=None, document_id_lower_limit=None, is_minor=False):
  149. page = start_page
  150. while num:
  151. url = "https://m.dcinside.com/board/{}?page={}".format(board_id, page)
  152. async with self.session.get(url) as res:
  153. text = await res.text()
  154. parsed = lxml.html.fromstring(text)
  155. doc_headers = (i[0] for i in parsed.xpath("//ul[contains(@class, 'gall-detail-lst')]/li") if not i.get("class", "").startswith("ad"))
  156. for doc in doc_headers:
  157. document_id = doc[0].get("href").split("/")[-1].split("?")[0]
  158. if document_id_upper_limit and int(document_id_upper_limit) <= int(document_id): continue
  159. if document_id_lower_limit and int(document_id_lower_limit) >= int(document_id): return
  160. if len(doc[0][1]) == 5:
  161. subject = doc[0][1][0].text
  162. author = doc[0][1][1].text
  163. time= self.__parse_time(doc[0][1][2].text)
  164. view_count= int(doc[0][1][3].text.split()[-1])
  165. voteup_count= int(doc[0][1][4][0].text.split()[-1])
  166. else:
  167. subject = None
  168. author = doc[0][1][0].text
  169. time= self.__parse_time(doc[0][1][1].text)
  170. view_count= int(doc[0][1][2].text.split()[-1])
  171. voteup_count= int(doc[0][1][3].text_content().split()[-1])
  172. title = doc[0][0][1].text
  173. indexdata = DocumentIndex(
  174. id= document_id,
  175. board_id=board_id,
  176. title= title,
  177. has_image= doc[0][0][0].get("class").endswith("img"),
  178. author= author,
  179. view_count= view_count,
  180. voteup_count= voteup_count,
  181. comment_count= int(doc[1][0].text),
  182. document= lambda: self.document(board_id, document_id),
  183. comments= lambda: self.comments(board_id, document_id),
  184. time= time,
  185. subject=subject
  186. )
  187. yield(indexdata)
  188. num-=1
  189. if num==0:
  190. break
  191. if not doc_headers:
  192. break
  193. else:
  194. page+=1
  195. async def document(self, board_id, document_id):
  196. url = "https://m.dcinside.com/board/{}/{}".format(board_id, document_id)
  197. async with self.session.get(url) as res:
  198. text = await res.text()
  199. parsed = lxml.html.fromstring(await res.text())
  200. doc_content_container = parsed.xpath("//div[@class='thum-txtin']")
  201. doc_head_containers = parsed.xpath("//div[@class='gallview-tit-box ']")
  202. if not len(doc_head_containers):
  203. return None
  204. doc_head_container = doc_head_containers[0]
  205. if len(doc_content_container):
  206. title = " ".join(doc_head_container[0].text.strip().split())
  207. author = doc_head_container[1][0][0].text.strip()
  208. author_id = None if len(doc_head_container[1]) <= 1 else doc_head_container[1][1][0].get("href").split("/")[-1]
  209. time = doc_head_container[1][0][1].text.strip()
  210. doc_content = parsed.xpath("//div[@class='thum-txtin']")[0]
  211. for adv in doc_content.xpath("div[@class='adv-groupin']"):
  212. adv.getparent().remove(adv)
  213. for adv in doc_content.xpath("//img"):
  214. if adv.get("src", "").startswith("https://nstatic") and not adv.get("data-original"):
  215. adv.getparent().remove(adv)
  216. return Document(
  217. id = document_id,
  218. board_id = board_id,
  219. title= title,
  220. author= author,
  221. author_id =author_id,
  222. contents= '\n'.join(i.strip() for i in doc_content.itertext() if i.strip() and not i.strip().startswith("이미지 광고")),
  223. images= [Image(
  224. src=i.get("data-original", i.get("src")),
  225. board_id=board_id,
  226. document_id=document_id,
  227. session=self.session)
  228. for i in doc_content.xpath("//img")
  229. if i.get("data-original") or (not i.get("src","").startswith("https://nstatic") and
  230. not i.get("src", "").startswith("https://img.iacstatic.co.kr") and i.get("src"))],
  231. html= lxml.html.tostring(doc_content, encoding=str),
  232. view_count= int(parsed.xpath("//ul[@class='ginfo2']")[1][0].text.strip().split()[1]),
  233. voteup_count= int(parsed.xpath("//span[@id='recomm_btn']")[0].text.strip()),
  234. votedown_count= int(parsed.xpath("//span[@id='nonrecomm_btn']")[0].text.strip()),
  235. logined_voteup_count= int(parsed.xpath("//span[@id='recomm_btn_member']")[0].text.strip()),
  236. comments= lambda: self.comments(board_id, document_id),
  237. time= self.__parse_time(time)
  238. )
  239. else:
  240. # fail due to unusual tags in mobile version
  241. # at now, just skip it
  242. return None
  243. ''' !TODO: use an alternative(PC) protocol to fetch document
  244. else:
  245. url = "https://gall.dcinside.com/{}?no={}".format(board_id, document_id)
  246. res = sess.get(url, timeout=TIMEOUT, headers=ALTERNATIVE_GET_HEADERS)
  247. parsed = lxml.html.fromstring(res.text)
  248. doc_content = parsed.xpath("//div[@class='thum-txtin']")[0]
  249. return '\n'.join(i.strip() for i in doc_content.itertext() if i.strip() and not i.strip().startswith("이미지 광고")), [i.get("src") for i in doc_content.xpath("//img") if not i.get("src","").startswith("https://nstatic")], comments(board_id, document_id, sess=sess)
  250. '''
  251. async def comments(self, board_id, document_id, num=-1, start_page=1):
  252. url = "https://m.dcinside.com/ajax/response-comment"
  253. for page in range(start_page, 999999):
  254. payload = {"id": board_id, "no": document_id, "cpage": page, "managerskill":"", "del_scope": "1", "csort": ""}
  255. async with self.session.post(url, headers=XML_HTTP_REQ_HEADERS, data=payload) as res:
  256. parsed = lxml.html.fromstring(await res.text())
  257. if not len(parsed[1].xpath("li")): break
  258. #for li in reversed(parsed[1].xpath("li")):
  259. for li in parsed[1].xpath("li"):
  260. if not len(li[0]): continue
  261. yield Comment(
  262. id= li.get("no"),
  263. parent_id= li.get("m_no"),
  264. author= li[0].text + ("{}".format(li[0][0].text) if li[0][0].text else ""),
  265. author_id= li[0][1].get("data-info", None) if len(li[0]) > 1 else None,
  266. contents= '\n'.join(i.strip() for i in li[1].itertext()),
  267. dccon= li[1][0].get("data-original", li[1][0].get("src", None)) if len(li[1]) and li[1][0].tag=="img" else None,
  268. voice= li[1][0].get("src", None) if len(li[1]) and li[1][0].tag=="iframe" else None,
  269. time= self.__parse_time(li[2].text))
  270. num -= 1
  271. if num == 0:
  272. return
  273. page_num_els = parsed.xpath("span[@class='pgnum']")
  274. if page_num_els:
  275. p = page_num_els[0].itertext()
  276. next(p)
  277. if page == next(p)[1:]:
  278. break
  279. else:
  280. break
  281. async def write_comment(self, board_id, document_id, contents="", dccon_id="", dccon_src="", parent_comment_id="", name="", password="", is_minor=False):
  282. url = "https://m.dcinside.com/board/{}/{}".format(board_id, document_id)
  283. async with self.session.get(url) as res:
  284. parsed = lxml.html.fromstring(await res.text())
  285. hide_robot = parsed.xpath("//input[@class='hide-robot']")[0].get("name")
  286. csrf_token = parsed.xpath("//meta[@name='csrf-token']")[0].get("content")
  287. title = parsed.xpath("//span[@class='tit']")[0].text.strip()
  288. board_name = parsed.xpath("//a[@class='gall-tit-lnk']")[0].text.strip()
  289. con_key = await self.__access("com_submit", url, require_conkey=False, csrf_token=csrf_token)
  290. header = XML_HTTP_REQ_HEADERS.copy()
  291. header["Referer"] = url
  292. header["Host"] = "m.dcinside.com"
  293. header["Origin"] = "https://m.dcinside.com"
  294. header["X-CSRF-TOKEN"] = csrf_token
  295. cookies = {
  296. "m_dcinside_" + board_id: board_id,
  297. "m_dcinside_lately": quote(board_id + "|" + board_name + ","),
  298. "_ga": "GA1.2.693521455.1588839880",
  299. }
  300. url = "https://m.dcinside.com/ajax/comment-write"
  301. payload = {
  302. "comment_memo": contents,
  303. "comment_nick": name,
  304. "comment_pw": password,
  305. "mode": "com_write",
  306. "comment_no": parent_comment_id,
  307. "id": board_id,
  308. "no": document_id,
  309. "best_chk": "",
  310. "subject": title,
  311. "board_id": "0",
  312. "reple_id":"",
  313. "cpage": "1",
  314. "con_key": con_key,
  315. hide_robot: "1",
  316. }
  317. if dccon_id: payload["detail_idx"] = dccon_id
  318. if dccon_src: payload["comment_memo"] = "<img src='{}' class='written_dccon' alt='1'>".format(dccon_src)
  319. #async with self.session.post(url, headers=header, data=payload, cookies=cookies) as res:
  320. async with self.session.post(url, headers=header, data=payload, cookies=cookies) as res:
  321. parsed = await res.text()
  322. try:
  323. parsed = json.loads(parsed)
  324. except Exception as e:
  325. raise Exception("Error while writing comment: " + unquote(str(parsed)))
  326. if "data" not in parsed:
  327. raise Exception("Error while writing comment: " + unquote(str(parsed)))
  328. return str(parsed["data"])
  329. async def modify_document(self, board_id, document_id, title="", contents="", name="", password="", is_minor=False):
  330. if not password:
  331. url = "https://m.dcinside.com/write/{}/modify/{}".format(board_id, document_id)
  332. async with self.session.get(url) as res:
  333. return await self.__write_or_modify_document(board_id, title, contents, name, password, intermediate=await res.text(), intermediate_referer=url, document_id=document_id, is_minor=is_minor)
  334. url = "https://m.dcinside.com/confirmpw/{}/{}?mode=modify".format(board_id, document_id)
  335. referer = url
  336. async with self.session.get(url) as res:
  337. parsed = lxml.html.fromstring(await res.text())
  338. token = parsed.xpath("//input[@name='_token']")[0].get("value", "")
  339. csrf_token = parsed.xpath("//meta[@name='csrf-token']")[0].get("content")
  340. con_key = await self.__access("Modifypw", url, require_conkey=False, csrf_token=csrf_token)
  341. payload = {
  342. "_token": token,
  343. "board_pw": password,
  344. "id": board_id,
  345. "no": document_id,
  346. "mode": "modify",
  347. "con_key": con_key,
  348. }
  349. header = XML_HTTP_REQ_HEADERS.copy()
  350. header["Referer"] = referer
  351. header["Host"] = "m.dcinside.com"
  352. header["Origin"] = "https://m.dcinside.com"
  353. header["X-CSRF-TOKEN"] = csrf_token
  354. url = "https://m.dcinside.com/ajax/pwcheck-board"
  355. async with self.session.post(url, headers=header, data=payload) as res:
  356. res = await res.text()
  357. if not res.strip():
  358. Exception("Error while modifing: maybe the password is incorrect")
  359. payload = {
  360. "board_pw": password,
  361. "id": board_id,
  362. "no": document_id,
  363. "_token": csrf_token
  364. }
  365. header = POST_HEADERS.copy()
  366. header["Referer"] = referer
  367. url = "https://m.dcinside.com/write/{}/modify/{}".format(board_id, document_id)
  368. async with self.session.post(url, headers=header, data=payload) as res:
  369. return await self.__write_or_modify_document(board_id, title, contents, name, password, intermediate=await res.text(), intermediate_referer=url, document_id=document_id)
  370. async def remove_document(self, board_id, document_id, password="", is_minor=False):
  371. if not password:
  372. url = "https://m.dcinside.com/board/{}/{}".format(board_id, document_id)
  373. async with self.session.get(url) as res:
  374. parsed = lxml.html.fromstring(await res.text())
  375. csrf_token = parsed.xpath("//meta[@name='csrf-token']")[0].get("content")
  376. header = XML_HTTP_REQ_HEADERS.copy()
  377. header["Referer"] = url
  378. header["X-CSRF-TOKEN"] = csrf_token
  379. con_key = await self.__access("board_Del", url, require_conkey=False, csrf_token=csrf_token)
  380. url = "https://m.dcinside.com/del/board"
  381. payload = { "id": board_id, "no": document_id, "con_key": con_key }
  382. async with self.session.post(url, headers=header, data=payload) as res:
  383. res = await res.text()
  384. if res.find("true") < 0:
  385. raise Exception("Error while removing: " + unquote(str(res)))
  386. return True
  387. url = "https://m.dcinside.com/confirmpw/{}/{}?mode=del".format(board_id, document_id)
  388. referer = url
  389. async with self.session.get(url) as res:
  390. parsed = lxml.html.fromstring(await res.text())
  391. token = parsed.xpath("//input[@name='_token']")[0].get("value", "")
  392. csrf_token = parsed.xpath("//meta[@name='csrf-token']")[0].get("content")
  393. board_name = parsed.xpath("//a[@class='gall-tit-lnk']")[0].text.strip()
  394. con_key = await self.__access("board_Del", url, require_conkey=False, csrf_token=csrf_token)
  395. payload = {
  396. "_token": token,
  397. "board_pw": password,
  398. "id": board_id,
  399. "no": document_id,
  400. "mode": "del",
  401. "con_key": con_key,
  402. }
  403. header = XML_HTTP_REQ_HEADERS.copy()
  404. header["Referer"] = url
  405. header["X-CSRF-TOKEN"] = csrf_token
  406. cookies = {
  407. "m_dcinside_" + board_id: board_id,
  408. "m_dcinside_lately": quote(board_id + "|" + board_name + ","),
  409. "_ga": "GA1.2.693521455.1588839880",
  410. }
  411. url = "https://m.dcinside.com/del/board"
  412. async with self.session.post(url, headers=header, data=payload, cookies=cookies) as res:
  413. res = await res.text()
  414. if res.find("true") < 0:
  415. raise Exception("Error while removing: " + unquote(str(res)))
  416. return True
  417. async def write_document(self, board_id, title="", contents="", name="", password="", is_minor=False):
  418. return await self.__write_or_modify_document(board_id, title, contents, name, password, is_minor=is_minor)
  419. async def __write_or_modify_document(self, board_id, title="", contents="", name="", password="", intermediate=None, intermediate_referer=None, document_id=None, is_minor=False):
  420. if not intermediate:
  421. url = "https://m.dcinside.com/write/{}".format(board_id)
  422. async with self.session.get(url) as res:
  423. parsed = lxml.html.fromstring(await res.text())
  424. else:
  425. parsed = lxml.html.fromstring(intermediate)
  426. url = intermediate_referer
  427. first_url = url
  428. rand_code = parsed.xpath("//input[@name='code']")
  429. rand_code = rand_code[0].get("value") if len(rand_code) else None
  430. user_id = parsed.xpath("//input[@name='user_id']")[0].get("value") if not name else None
  431. mobile_key = parsed.xpath("//input[@id='mobile_key']")[0].get("value")
  432. hide_robot = parsed.xpath("//input[@class='hide-robot']")[0].get("name")
  433. csrf_token = parsed.xpath("//meta[@name='csrf-token']")[0].get("content")
  434. con_key = await self.__access("dc_check2", url, require_conkey=False, csrf_token=csrf_token)
  435. board_name = parsed.xpath("//a[@class='gall-tit-lnk']")[0].text.strip()
  436. header = XML_HTTP_REQ_HEADERS.copy()
  437. header["Referer"] = url
  438. header["X-CSRF-TOKEN"] = csrf_token
  439. url = "https://m.dcinside.com/ajax/w_filter"
  440. payload = {
  441. "subject": title,
  442. "memo": contents,
  443. "mode": "write",
  444. "id": board_id,
  445. }
  446. if rand_code:
  447. payload["code"] = rand_code
  448. async with self.session.post(url, headers=header, data=payload) as res:
  449. res = await res.text()
  450. res = json.loads(res)
  451. if not res["result"]:
  452. raise Exception("Erorr while write document: " + str(res))
  453. header = POST_HEADERS.copy()
  454. url = "https://mupload.dcinside.com/write_new.php"
  455. header["Host"] = "mupload.dcinside.com"
  456. header["Referer"] = first_url
  457. payload = {
  458. "subject": title,
  459. "memo": contents,
  460. hide_robot: "1",
  461. "GEY3JWF": hide_robot,
  462. "id": board_id,
  463. "contentOrder": "order_memo",
  464. "mode": "write",
  465. "Block_key": con_key,
  466. "bgm":"",
  467. "iData":"",
  468. "yData":"",
  469. "tmp":"",
  470. "imgSize": "850",
  471. "is_minor": "1" if is_minor else "",
  472. "mobile_key": mobile_key,
  473. "GEY3JWF": hide_robot,
  474. }
  475. if rand_code:
  476. payload["code"] = rand_code
  477. if name:
  478. payload["name"] = name
  479. payload["password"] = password
  480. else:
  481. payload["user_id"] = user_id
  482. if intermediate:
  483. payload["mode"] = "modify"
  484. payload["delcheck"] = ""
  485. payload["t_ch2"] = ""
  486. payload["no"] = document_id
  487. cookies = {
  488. "m_dcinside_" + board_id: board_id,
  489. "m_dcinside_lately": quote(board_id + "|" + board_name + ","),
  490. "_ga": "GA1.2.693521455.1588839880",
  491. }
  492. async with self.session.post(url, headers=header, data=payload, cookies=cookies) as res:
  493. res = await res.text()
  494.  
  495. async def __access(self, token_verify, target_url, require_conkey=True, csrf_token=None):
  496. if require_conkey:
  497. async with self.session.get(target_url) as res:
  498. parsed = lxml.html.fromstring(await res.text())
  499. con_key = parsed.xpath("//input[@id='con_key']")[0].get("value")
  500. payload = { "token_verify": token_verify, "con_key": con_key }
  501. else:
  502. payload = { "token_verify": token_verify, }
  503. url = "https://m.dcinside.com/ajax/access"
  504. headers = XML_HTTP_REQ_HEADERS.copy()
  505. headers["Referer"] = target_url
  506. headers["X-CSRF-TOKEN"] = csrf_token
  507. async with self.session.post(url, headers=headers, data=payload) as res:
  508. return (await res.json())["Block_key"]
  509. def __parse_time(self, time):
  510. today = datetime.now()
  511. if len(time) <= 5:
  512. if time.find(":") > 0:
  513. return datetime.strptime(time, "%H:%M").replace(year=today.year, month=today.month, day=today.day)
  514. else:
  515. return datetime.strptime(time, "%m.%d").replace(year=today.year, hour=23, minute=59, second=59)
  516. elif len(time) <= 11:
  517. if time.find(":") > 0:
  518. return datetime.strptime(time, "%m.%d %H:%M").replace(year=today.year)
  519. else:
  520. return datetime.strptime(time, "%y.%m.%d").replace(year=today.year, hour=23, minute=59, second=59)
  521. elif len(time) <= 16:
  522. if time.count(".") >= 2:
  523. return datetime.strptime(time, "%Y.%m.%d %H:%M")
  524. else:
  525. return datetime.strptime(time, "%m.%d %H:%M:%S").replace(year=today.year)
  526. else:
  527. if "." in time:
  528. return datetime.strptime(time, "%Y.%m.%d %H:%M:%S")
  529. else:
  530. return datetime.strptime(time, "%Y-%m-%d %H:%M:%S")
  531.  
Advertisement
Add Comment
Please, Sign In to add comment