API tools faq
paste
Advertisement
nicuf

asa

nicuf
Oct 24th, 2023
93
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 29.41 KB | None | 0 0
raw download clone embed print report
  1. #-------------------------------------------------------------------------------
  2. # Name: module1
  3. # Purpose:
  4. #
  5. # Author: Castel
  6. #
  7. # Created: 22/01/2022
  8. # Copyright: (c) Castel 2022
  9. # Licence: <your licence>
  10. #-------------------------------------------------------------------------------
  11.  
  12. import os
  13. import re
  14.  
  15. def read_text_from_file(file_path):
  16. """
  17. Aceasta functie returneaza continutul unui fisier.
  18. file_path: calea catre fisierul din care vrei sa citesti
  19. """
  20. with open(file_path, encoding='utf8') as f:
  21. text = f.read()
  22. return text
  23.  
  24.  
  25. def write_to_file(text, file_path):
  26. """
  27. Aceasta functie scrie un text intr-un fisier.
  28. text: textul pe care vrei sa il scrii
  29. file_path: calea catre fisierul in care vrei sa scrii
  30. """
  31. with open(file_path, 'wb') as f:
  32. f.write(text.encode('utf8', 'ignore'))
  33.  
  34.  
  35. def copiaza_continut_html(cale_fisier_html, cale_fisiere_gata): # astea sunt argumentele functiei, adica cand apelez functia
  36. # citesti textul din fisierul html
  37. text_html = read_text_from_file(cale_fisier_html)
  38. final_text = ''
  39.  
  40. # === fisier html vechi ===
  41. articol_categorie_pattern = re.compile('<!-- ARTICOL CATEGORIE START -->([\s\S]*?)<!-- ARTICOL CATEGORIE FINAL -->')
  42. articol_categorie = re.findall(articol_categorie_pattern, text_html)
  43. if len(articol_categorie) != 0:
  44. # === citire fisier model - index2.html ===
  45. text_html_model = read_text_from_file("C:\\Folder1\\index2.html")
  46. articol_categorie = articol_categorie[0]
  47.  
  48. # ==== INLOCUIRE <td><span class="den_articol"> CU <td><span class="linkMare"> ====
  49. span_pattern = re.compile('<td><span class="den_articol"><a href=\"(.*?)\" class="linkMare">(.*?)</a></span></td>')
  50. span_nou = '<td><span class="linkMare"><a href="{}" class="linkMare"><span class="den_articol">{}</span></a></span></td>'
  51. span = re.findall(span_pattern, articol_categorie)
  52. lista_span_nou = list()
  53. for i in range(len(span)):
  54. lista_span_nou.append(span_nou.format(span[i][0], span[i][1]))
  55. span_pattern = re.compile('<td><span class="den_articol"><a href=\".*?\" class="linkMare">.*?</a></span></td>')
  56. span = re.findall(span_pattern, articol_categorie)
  57. for i in range(len(span)):
  58. articol_categorie = articol_categorie.replace(span[i], lista_span_nou[i])
  59. # ==== INLOCUIRE <td><span class="den_articol"> CU <td><span class="linkMare"> ====
  60.  
  61. # ==== Informatii fisier original ====
  62. categ_link_title_pattern = re.compile('<td><span class="linkMare"><a href="(.*?)" class="linkMare"><span class="den_articol">(.*?)</span></a></span></td>')
  63. categ_link_title = re.findall(categ_link_title_pattern, articol_categorie)
  64. print("Total {} ARTICOLE".format(len(categ_link_title)))
  65. categ_date_link_title_desc_pattern = re.compile('<td class="text_dreapta">(.*?)<a href=\"(.*?)\" title=\"(.*?)\" class="external" rel="category tag">(.*?)</a>, by Neculai Fantanaru</td>')
  66. categ_date_link_title_desc = re.findall(categ_date_link_title_desc_pattern, articol_categorie)
  67. paragraf_pattern = re.compile('<p class="text_obisnuit2"><em>(.*?)</em></p>')
  68. paragraf = re.findall(paragraf_pattern, articol_categorie)
  69.  
  70. print("PARAGRAF", len(paragraf))
  71.  
  72. # === citeste mai departe - buton ===
  73. citeste_buton_pattern = re.compile('<div align="right" id="external2"><a href=\"(.*?)\">cite&#351;te mai departe </a>')
  74. citeste_buton = re.findall(citeste_buton_pattern, articol_categorie)
  75. read_more_buton_pattern = re.compile('<div align="right" id="external2"><a href=\"(.*?)\">read more </a>')
  76. read_more_buton = re.findall(read_more_buton_pattern, articol_categorie)
  77.  
  78. # === Informatii index2 ===
  79. articol_categorie_index2_pattern = re.compile('<!-- ARTICOL START -->([\s\S]*?)<!-- ARTICOL FINAL -->')
  80. articol_categorie_index2 = re.findall(articol_categorie_index2_pattern, text_html_model)
  81. if len(articol_categorie_index2) != 0:
  82. articol_categorie_index2 = articol_categorie_index2[0] # trebuie inlocuit cu toate categoriile din fisierul original
  83. # citire template pentru categorie din index2.html
  84. template_categorie = read_text_from_file("C:\\Folder1\\template_categorie.txt")
  85.  
  86. # h3 => title + description
  87. h3_pattern = re.compile('<h3 class="font-weight-normal" itemprop="name"><a href=\"(.*?)\" class="color-black">(.*?)</a></h3>')
  88. h3 = re.findall(h3_pattern, template_categorie)
  89. h3 = h3[0]
  90. # dates section din index2.html
  91. dates_section_index2_pattern = re.compile('<!--STARTDATES-->([\s\S]*?)<!--FINNISHDATES-->')
  92. dates_section_index2 = re.findall(dates_section_index2_pattern, template_categorie)
  93. dates_section_index2 = dates_section_index2[0]
  94. date_index2_pattern = re.compile('<a href="javascript:void\(0\)" class="color-black">(.*?)</a>')
  95. # date
  96. date_index2 = re.findall(date_index2_pattern, dates_section_index2)
  97. date_index2 = date_index2[0]
  98. # link / title / description
  99. link_title_desc_index2_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\" class="color-green font-weight-600 mx-1" id="hidden">(.*?)</a>')
  100. link_title_desc_index2 = re.findall(link_title_desc_index2_pattern, dates_section_index2)
  101. link_title_desc_index2 = link_title_desc_index2[0]
  102.  
  103. # paragraf
  104. paragraf_index2_pattern = re.compile('<p class="mb-35px color-grey line-height-25px">(.*?)</p>')
  105. paragraf_index2 = re.findall(paragraf_index2_pattern, template_categorie)
  106. paragraf_index2 = paragraf_index2[0]
  107.  
  108. # === read more ===
  109. read_more_pattern = re.compile('<a href=\"(.*?)\" class="btn-setting color-black btn-hvr-up btn-blue btn-hvr-pink">read more</a>')
  110. read_more = re.findall(read_more_pattern, template_categorie)
  111. read_more = read_more[0]
  112.  
  113. butoane = list()
  114. if len(citeste_buton) > 0:
  115. butoane = citeste_buton
  116. else:
  117. butoane = read_more_buton
  118. print("CATEGORIE", len(categ_link_title))
  119. for i in range(len(categ_link_title)):
  120. new_template = template_categorie
  121. # === facem replace cu informatiile din articolul original ===
  122. new_template_1 = new_template.replace(date_index2, categ_date_link_title_desc[i][0].replace(', in', '').strip())
  123. new_template_2 = new_template_1.replace(link_title_desc_index2[0], categ_date_link_title_desc[i][1])
  124. new_template_3 = new_template_2.replace(link_title_desc_index2[1], categ_date_link_title_desc[i][2])
  125. new_template_4 = new_template_3.replace(link_title_desc_index2[2], categ_date_link_title_desc[i][3].lstrip())
  126. new_template_5 = new_template_4.replace(paragraf_index2, paragraf[i])
  127. new_template_6 = new_template_5.replace(read_more, butoane[i])
  128. new_template_7 = new_template_6.replace(h3[0], categ_link_title[i][0])
  129. new_template_8 = new_template_7.replace(h3[1], categ_link_title[i][1])
  130. final_text = final_text + new_template_8 + '\n'
  131.  
  132. text_html_model = text_html_model.replace(articol_categorie_index2, final_text)
  133. final_text = text_html_model
  134.  
  135. # schimbare CATEGORIES index2
  136. # preluare lista fisier html
  137. lista_pattern = re.compile('<ul id="sidebarNavigation">([\s\S]*?)</ul>')
  138. lista = re.findall(lista_pattern, text_html)
  139. if len(lista) != 0:
  140. lista = lista[0]
  141. elemente_lista_pattern = re.compile('<li><a href=\"(.*?)\" title=\"(.*?)\">(.*?) \((.*?)\)</a></li>')
  142. elemente_lista = re.findall(elemente_lista_pattern, lista)
  143. if elemente_lista != 0:
  144. categories_pattern = re.compile('<!-- Categories -->([\s\S]*?)<!-- BOOKS START -->')
  145. categories = re.findall(categories_pattern, final_text)
  146. if len(categories) != 0:
  147. categories = categories[0]
  148. elemente_lista_model_pattern = re.compile('<div class="categories-name">([\s\S]*?)</div>')
  149. elemente_lista_model = re.findall(elemente_lista_model_pattern, categories)
  150. template_category = read_text_from_file('C:\\Folder1\\category-name.txt')
  151.  
  152. for i in range(len(elemente_lista_model)):
  153. new_template_category = template_category
  154. a_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\">')
  155. a = re.findall(a_pattern, new_template_category)[0]
  156. p_pattern = re.compile('<p class="font-16 color-grey text-capitalize"><i class="fa fa-angle-right font-14 color-blue mr-1"></i> (.*?) <span>(.*?)</span> </p>')
  157. p = re.findall(p_pattern, new_template_category)[0]
  158. new_template_category = new_template_category.replace(a[0], elemente_lista[i][0])
  159. new_template_category = new_template_category.replace(a[1], elemente_lista[i][1])
  160. new_template_category = new_template_category.replace(p[0], elemente_lista[i][2])
  161. new_template_category = new_template_category.replace(p[1], elemente_lista[i][3])
  162. # print(final_text)
  163. final_text = final_text.replace(elemente_lista_model[i], new_template_category)
  164.  
  165. else:
  166. print("No categories + books start")
  167. else:
  168. print("Niciun element <li>.")
  169. else:
  170. print("Tag <ul> gol.")
  171.  
  172.  
  173. # Shimbare LINK-URI FLAGS
  174. flags_pattern = re.compile('<!-- FLAGS_1 -->([\s\S]*?)<!-- FLAGS -->')
  175. flags = re.findall(flags_pattern, text_html)
  176. if len(flags) != 0:
  177. flags = flags[0]
  178. links_pattern = re.compile('<a href=\"(.*?)\">')
  179. links = re.findall(links_pattern, flags)
  180. if len(links) != 0:
  181. # print("Links: ", links)
  182. flags_model = re.findall(flags_pattern, final_text)
  183. if len(flags_model) != 0:
  184. flags_model = flags_model[0]
  185. links_pattern_model = re.compile('<li><a cunt_code=\"\+\d+\" href=\"(.*?)\">')
  186. links_model = re.findall(links_pattern_model, flags_model)
  187. if len(links_model) != 0:
  188. for i in range(len(links)):
  189. # print(links[i], links_model[i])
  190. final_text = final_text.replace(links_model[i], links[i]) # FACE REPLACE
  191. else:
  192. print("Fara links in flags model")
  193. else:
  194. print("Fara links in flags model")
  195. else:
  196. print("Fara linkuri in flags.")
  197. else:
  198. print("Fara flags in articol original.")
  199.  
  200. # STARS - PHP
  201. stars_php_pattern = re.compile('\$item_id = (.*?);')
  202. stars_php = re.findall(stars_php_pattern, text_html)
  203. stars_php_model = re.findall(stars_php_pattern, final_text)
  204. if len(stars_php) != 0:
  205. stars_php = stars_php[0]
  206. if len(stars_php_model) != 0:
  207. stars_php_model = stars_php_model[0]
  208. final_text = final_text.replace(stars_php_model, stars_php) # FACE REPLACE
  209. else:
  210. print("No stars fisier model")
  211. else:
  212. print("No stars fisier original")
  213.  
  214. # TITLE
  215. title_pattern = re.compile('<title>(.*?)</title>')
  216. text_title = re.findall(title_pattern, text_html)
  217. text_title_model = re.findall(title_pattern, final_text)
  218. if len(text_title) != 0 and len(text_title_model) != 0:
  219. text_title = text_title[0]
  220. text_title_model = text_title_model[0]
  221. final_text = final_text.replace(text_title_model, text_title)
  222. else:
  223. print("Fisier html fara tag title: {}".format(cale_fisier_html))
  224.  
  225. # DESCRIPTION
  226. description_pattern = re.compile('<meta name="description" content="(.*?)">')
  227. text_description = re.findall(description_pattern, text_html)
  228. text_description_model = re.findall(description_pattern, final_text)
  229. if len(text_description) != 0 and len(text_description_model) != 0:
  230. text_description = text_description[0]
  231. text_description_model = text_description_model[0]
  232. final_text = final_text.replace(text_description_model, text_description)
  233. else:
  234. print("Fisier html fara tag description: {}".format(cale_fisier_html))
  235.  
  236. # CANONICAL
  237. canonical_pattern = re.compile('<link rel="canonical" href="(.*?)" />')
  238. text_canonical = re.findall(canonical_pattern, text_html)
  239. text_canonical_model = re.findall(canonical_pattern, final_text)
  240. if len(text_canonical) != 0 and len(text_canonical_model) != 0:
  241. text_canonical = text_canonical[0]
  242. text_canonical_model = text_canonical_model[0]
  243. final_text = final_text.replace(text_canonical_model, text_canonical)
  244. else:
  245. print("Fisier html fara tag canonical: {}".format(cale_fisier_html))
  246.  
  247. # ULTIMELE ARTICOLE
  248. ult_art_pattern = re.compile('<!-- Ultimele articole -->([\s\S]*?)<!-- Ultimele articole final -->')
  249. ult_art_model_pattern = re.compile('<!-- Recent Post -->([\s\S]*?)<!-- Categories -->')
  250. ult_art = re.findall(ult_art_pattern, text_html)
  251. ult_art_model = re.findall(ult_art_model_pattern, final_text)
  252. if len(ult_art) != 0:
  253. ult_art = ult_art[0]
  254. if len(ult_art_model) != 0:
  255. ult_art_model = ult_art_model[0]
  256. articole_pattern = re.compile('<li><a href=\"(.*?)\">(.*?)</a></li>')
  257. articole = re.findall(articole_pattern, ult_art)
  258. if len(articole) != 0:
  259. articole_model_pattern = re.compile('<a href=\"(.*?)\" class="color-grey">(.*?)</a>')
  260. articole_model = re.findall(articole_model_pattern, ult_art_model)
  261. if len(articole_model) != 0:
  262. for i in range(len(articole)):
  263. # href - 0 / description - 1
  264. final_text = final_text.replace(articole_model[i][0], articole[i][0])
  265. final_text = final_text.replace(articole_model[i][1], articole[i][1])
  266. else:
  267. print("No articole fisier model")
  268. else:
  269. print("No articole fisier original")
  270. else:
  271. print("No lista articole fisier model")
  272. else:
  273. print("No lista articole fisier original")
  274.  
  275. else:
  276. print("Nu exista articol categorie in index2.html")
  277. else:
  278. # === citire fisier model - index.html ===
  279. text_html_model = read_text_from_file("C:\\Folder1\\index.html")
  280. # ARTICOL START - FINAL
  281. articol_pattern = re.compile('<!-- ARTICOL START -->([\s\S]*?)<!-- ARTICOL FINAL -->[\s\S]*?')
  282. text_articol = re.findall(articol_pattern, text_html)
  283. text_articol_model = re.findall(articol_pattern, text_html_model)
  284. if len(text_articol) != 0 and len(text_articol_model) != 0:
  285. text_articol = text_articol[0]
  286. text_articol_model = text_articol_model[0]
  287. text_html_model_1 = text_html_model.replace(text_articol_model, text_articol)
  288. final_text = text_html_model_1
  289. else:
  290. print("Fisier html fara ARTICOL START/FINAL: {}".format(cale_fisier_html))
  291.  
  292. # TITLE
  293. title_pattern = re.compile('<title>(.*?)</title>')
  294. text_title = re.findall(title_pattern, text_html)
  295. text_title_model = re.findall(title_pattern, text_html_model_1)
  296. if len(text_title) != 0 and len(text_title_model) != 0:
  297. text_title = text_title[0]
  298. text_title_model = text_title_model[0]
  299. text_html_model_2 = text_html_model_1.replace(text_title_model, text_title)
  300. final_text = text_html_model_2
  301. else:
  302. print("Fisier html fara tag title: {}".format(cale_fisier_html))
  303.  
  304. # DESCRIPTION
  305. description_pattern = re.compile('<meta name="description" content="(.*?)">')
  306. text_description = re.findall(description_pattern, text_html)
  307. text_description_model = re.findall(description_pattern, text_html_model_2)
  308. if len(text_description) != 0 and len(text_description_model) != 0:
  309. text_description = text_description[0]
  310. text_description_model = text_description_model[0]
  311. text_html_model_3 = text_html_model_2.replace(text_description_model, text_description)
  312. final_text = text_html_model_3
  313. else:
  314. print("Fisier html fara tag description: {}".format(cale_fisier_html))
  315.  
  316. # CANONICAL
  317. canonical_pattern = re.compile('<link rel="canonical" href="(.*?)" />')
  318. text_canonical = re.findall(canonical_pattern, text_html)
  319. text_canonical_model = re.findall(canonical_pattern, text_html_model_3)
  320. if len(text_canonical) != 0 and len(text_canonical_model) != 0:
  321. text_canonical = text_canonical[0]
  322. text_canonical_model = text_canonical_model[0]
  323. text_html_model_4 = text_html_model_3.replace(text_canonical_model, text_canonical)
  324. final_text = text_html_model_4
  325. else:
  326. print("Fisier html fara tag canonical: {}".format(cale_fisier_html))
  327.  
  328.  
  329. # remove DIV tag and TABLE tag
  330. text_articol_model = re.findall(articol_pattern, text_html_model_4)
  331. text_articol_model_old = text_articol_model[0]
  332. text_articol_model = text_articol_model[0]
  333. text_articol_model = text_articol_model.replace("<div align=\"justify\">", '')
  334. text_articol_model = text_articol_model.replace("</div>", '')
  335.  
  336. table_pattern = re.compile('<table[\s\S]*?</table>')
  337. text_table = re.findall(table_pattern, text_articol_model)
  338. if len(text_table) != 0:
  339. text_table = text_table[0]
  340. text_articol_model = text_articol_model.replace(text_table, '')
  341. text_html_model_5 = text_html_model_4.replace(text_articol_model_old, text_articol_model)
  342. final_text = text_html_model_5
  343. else:
  344. print("No text table")
  345.  
  346. # schimbare tag-uri ARTICLE TITLE
  347. article_title_pattern = re.compile('<h1 class="den_articol" itemprop="name">(.*?)</h1>')
  348. article_title = re.findall(article_title_pattern, text_articol_model_old)
  349. if len(article_title) != 0:
  350. article_title = article_title[0]
  351. h3_title_pattern = re.compile('<h3 class="font-weight-normal" itemprop="name"><a href="javascript:void\(0\)" class="color-black">(.*?)</a></h3>')
  352. h3_title = re.findall(h3_title_pattern, text_html_model_5)
  353. if len(h3_title) != 0:
  354. h3_title = h3_title[0]
  355. text_html_model_6 = text_html_model_5.replace(h3_title, article_title)
  356. final_text = text_html_model_6
  357. else:
  358. print("No h3 title.")
  359. else:
  360. print("No article title.")
  361.  
  362. # schimbare DATE
  363. date_pattern = re.compile('<td class="text_dreapta">(.*?), in <a')
  364. date = re.findall(date_pattern, text_articol_model_old)
  365. if len(date) != 0:
  366. date = date[0]
  367. # MODIFICARE 09/03
  368. date_section_pattern = re.compile('<!--STARTDATES-->([\s\S]*?)<!--FINNISHDATES-->')
  369. date_section = re.findall(date_section_pattern, text_html_model_6)
  370. if len(date_section) > 0:
  371. date_section = date_section[0]
  372. date_pattern_model = re.compile('<a href="javascript:void\(0\)" class="color-black">(.*?)</a>')
  373. date_model = re.findall(date_pattern_model, date_section)
  374. if len(date_model) != 0:
  375. date_model = date_model[0]
  376. text_html_model_7 = text_html_model_6.replace(date_model, date)
  377. final_text = text_html_model_7
  378. else:
  379. print('No date in model.')
  380. else:
  381. print("No date section: <!--STARTDATES--><!--FINNISHDATES-->")
  382. else:
  383. print("No date.")
  384.  
  385. # schimbare SECTION
  386. section_pattern_model = re.compile('<a href=\"(.*?)\" title=\"(.*?)\" class="color-green font-weight-600 mx-1" id="hidden">(.*?)</a>')
  387. section_model = re.findall(section_pattern_model, text_html_model_7)
  388. # print(section_model)
  389. if len(section_model) != 0:
  390. section_model = section_model[0]
  391. section_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\" class="external" rel="category tag">(.*?)</a>')
  392. section = re.findall(section_pattern, text_articol_model_old)
  393. if len(section) != 0:
  394. section = section[0]
  395. text_html_model_8 = text_html_model_7.replace(section_model[0], section[0])
  396. text_html_model_9 = text_html_model_8.replace(section_model[1], section[1])
  397. text_html_model_10 = text_html_model_9.replace(section_model[2], section[2])
  398. final_text = text_html_model_10
  399. else:
  400. print("No section.")
  401. else:
  402. print("No section model.")
  403.  
  404. # schimbare CATEGORIES
  405. # preluare lista fisier html
  406. lista_pattern = re.compile('<ul id="sidebarNavigation">([\s\S]*?)</ul>')
  407. lista = re.findall(lista_pattern, text_html)
  408. if len(lista) != 0:
  409. lista = lista[0]
  410. elemente_lista_pattern = re.compile('<li><a href=\"(.*?)\" title=\"(.*?)\">(.*?) \((.*?)\)</a></li>')
  411. elemente_lista = re.findall(elemente_lista_pattern, lista)
  412. if elemente_lista != 0:
  413. categories_pattern = re.compile('<!-- Categories -->([\s\S]*?)<!-- BOOKS START -->')
  414. categories = re.findall(categories_pattern, text_html_model_10)
  415. if len(categories) != 0:
  416. categories = categories[0]
  417. elemente_lista_model_pattern = re.compile('<div class="categories-name">([\s\S]*?)</div>')
  418. elemente_lista_model = re.findall(elemente_lista_model_pattern, categories)
  419. template_category = read_text_from_file('C:\\Folder1\\category-name.txt')
  420.  
  421. for i in range(len(elemente_lista_model)):
  422. new_template_category = template_category
  423. a_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\">')
  424. a = re.findall(a_pattern, new_template_category)[0]
  425. p_pattern = re.compile('<p class="font-16 color-grey text-capitalize"><i class="fa fa-angle-right font-14 color-blue mr-1"></i> (.*?) <span>(.*?)</span> </p>')
  426. p = re.findall(p_pattern, new_template_category)[0]
  427. new_template_category = new_template_category.replace(a[0], elemente_lista[i][0])
  428. new_template_category = new_template_category.replace(a[1], elemente_lista[i][1])
  429. new_template_category = new_template_category.replace(p[0], elemente_lista[i][2])
  430. new_template_category = new_template_category.replace(p[1], elemente_lista[i][3])
  431. # print(final_text)
  432. final_text = final_text.replace(elemente_lista_model[i], new_template_category)
  433. # print("==========================")
  434. # print(final_text)
  435. text_html_model_14 = final_text
  436. else:
  437. print("No categories + books start")
  438. else:
  439. print("Niciun element <li>.")
  440. else:
  441. print("Tag <ul> gol.")
  442.  
  443. # Shimbare LINK-URI FLAGS
  444. flags_pattern = re.compile('<!-- FLAGS_1 -->([\s\S]*?)<!-- FLAGS -->')
  445. flags = re.findall(flags_pattern, text_html)
  446. if len(flags) != 0:
  447. flags = flags[0]
  448. links_pattern = re.compile('<a href=\"(.*?)\">')
  449. links = re.findall(links_pattern, flags)
  450. if len(links) != 0:
  451. # print("Links: ", links)
  452. flags_model = re.findall(flags_pattern, text_html_model_14)
  453. if len(flags_model) != 0:
  454. flags_model = flags_model[0]
  455. # print("Flags: ", flags_model)
  456. links_pattern_model = re.compile('<li><a cunt_code=\"\+\d+\" href=\"(.*?)\">')
  457. links_model = re.findall(links_pattern_model, flags_model)
  458. # print(links_model)
  459. text_html_model_15 = text_html_model_14
  460. if len(links_model) != 0:
  461. for i in range(len(links)):
  462. # print(links[i], links_model[i])
  463. text_html_model_15 = text_html_model_15.replace(links_model[i], links[i]) # FACE REPLACE
  464. final_text = text_html_model_15
  465. else:
  466. print("Fara links in flags model")
  467. else:
  468. print("Fara links in flags model")
  469. else:
  470. print("Fara linkuri in flags.")
  471. else:
  472. print("Fara flags in articol original.")
  473.  
  474. # STARS - PHP
  475. stars_php_pattern = re.compile('\$item_id = (.*?);')
  476. stars_php = re.findall(stars_php_pattern, text_html)
  477. stars_php_model = re.findall(stars_php_pattern, text_html_model_15)
  478. if len(stars_php) != 0:
  479. stars_php = stars_php[0]
  480. if len(stars_php_model) != 0:
  481. stars_php_model = stars_php_model[0]
  482. text_html_model_16 = text_html_model_15.replace(stars_php_model, stars_php) # FACE REPLACE
  483. final_text = text_html_model_16
  484. else:
  485. print("No stars fisier model")
  486. else:
  487. print("No stars fisier original")
  488.  
  489. # ULTIMELE ARTICOLE
  490. ult_art_pattern = re.compile('<!-- Ultimele articole -->([\s\S]*?)<!-- Ultimele articole final -->')
  491. ult_art_model_pattern = re.compile('<!-- Recent Post -->([\s\S]*?)<!-- Categories -->')
  492. ult_art = re.findall(ult_art_pattern, text_html)
  493. ult_art_model = re.findall(ult_art_model_pattern, text_html_model_16)
  494. if len(ult_art) != 0:
  495. ult_art = ult_art[0]
  496. if len(ult_art_model) != 0:
  497. ult_art_model = ult_art_model[0]
  498. articole_pattern = re.compile('<li><a href=\"(.*?)\">(.*?)</a></li>')
  499. articole = re.findall(articole_pattern, ult_art)
  500. if len(articole) != 0:
  501. articole_model_pattern = re.compile('<a href=\"(.*?)\" class="color-grey">(.*?)</a>')
  502. articole_model = re.findall(articole_model_pattern, ult_art_model)
  503. if len(articole_model) != 0:
  504. for i in range(len(articole)):
  505. # href - 0 / description - 1
  506. # MODIFICARE 09/03
  507. final_text = final_text.replace(articole_model[i][0], articole[i][0])
  508. final_text = final_text.replace(articole_model[i][1], articole[i][1])
  509. else:
  510. print("No articole fisier model")
  511. else:
  512. print("No articole fisier original")
  513. else:
  514. print("No lista articole fisier model")
  515. else:
  516. print("No lista articole fisier original")
  517.  
  518. file_path = cale_fisiere_gata + "\\" + os.path.basename(cale_fisier_html)
  519. write_to_file(final_text, file_path)
  520. print("Scriere efectuata cu succes.")
  521.  
  522.  
  523.  
  524. def creare_fisiere_html(cale_folder_html, cale_fisiere_gata):
  525. """
  526. Functia itereaza printr-un folder care contine fisiere txt si creeaza fisiere html corespunzatoare
  527. """
  528. count = 0
  529. for f in os.listdir(cale_folder_html):
  530. if f.endswith('.html'):
  531. cale_fisier_html = cale_folder_html + "\\" + f
  532. print("FISIER CURENT: ", cale_fisier_html)
  533. copiaza_continut_html(cale_fisier_html, cale_fisiere_gata)
  534. count += 1
  535. else:
  536. continue
  537. print("Numarul de fisiere modificate: ", count)
  538.  
  539. def main():
  540. creare_fisiere_html("c:\\Folder1\\fisiere_html", "C:\\Folder1\\fisiere_gata")
  541.  
  542. if __name__ == '__main__':
  543. main()
  544.  
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!