API tools faq
paste
Advertisement
nicuf

Transfer data from a website to another website

nicuf
Mar 24th, 2022
992
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 29.60 KB | None | 0 0
raw download clone embed print report
  1. --------------------------------------
  2. EXPLANATION:
  3.  
  4. ROMANIAN: https://neculaifantanaru.com/python-transfer-data-from-a-website-to-another-website-design.html
  5. ENGLISH: https://neculaifantanaru.com/en/python-transfer-data-from-a-website-to-another-website-design.html
  6. --------------------------------------
  7.  
  8.  
  9.  
  10. #-------------------------------------------------------------------------------
  11. # Author:      Neculai Fantanaru
  12. #
  13. # Created:     24/03/2022
  14. # Copyright:   (c) Neculai Fantanaru
  15. # Licence:     <your licence>
  16. #-------------------------------------------------------------------------------
  17.  
  18. import os
  19. import re
  20.  
  21. def read_text_from_file(file_path):
  22.     """
  23.    Aceasta functie returneaza continutul unui fisier.
  24.    file_path: calea catre fisierul din care vrei sa citesti
  25.    """
  26.     with open(file_path, encoding='utf8') as f:
  27.         text = f.read()
  28.         return text
  29.  
  30.  
  31. def write_to_file(text, file_path):
  32.     """
  33.    Aceasta functie scrie un text intr-un fisier.
  34.    text: textul pe care vrei sa il scrii
  35.    file_path: calea catre fisierul in care vrei sa scrii
  36.    """
  37.     with open(file_path, 'wb') as f:
  38.         f.write(text.encode('utf8', 'ignore'))
  39.  
  40.  
  41. def copiaza_continut_html(cale_fisier_html, cale_fisiere_gata): # astea sunt argumentele functiei, adica cand apelez functia
  42.     # citesti textul din fisierul html
  43.     text_html = read_text_from_file(cale_fisier_html)
  44.     final_text = ''
  45.  
  46.     # === fisier html vechi ===
  47.     articol_categorie_pattern = re.compile('<!-- ARTICOL CATEGORIE START -->([\s\S]*?)<!-- ARTICOL CATEGORIE FINAL -->')
  48.     articol_categorie = re.findall(articol_categorie_pattern, text_html)
  49.     if len(articol_categorie) != 0:
  50.         # === citire fisier model - index2.html ===
  51.         text_html_model = read_text_from_file("C:\\Folder1\\index2.html")
  52.         articol_categorie = articol_categorie[0]
  53.  
  54.         # ==== INLOCUIRE <td><span class="den_articol"> CU <td><span class="linkMare"> ====
  55.         span_pattern = re.compile('<td><span class="den_articol"><a href=\"(.*?)\" class="linkMare">(.*?)</a></span></td>')
  56.         span_nou = '<td><span class="linkMare"><a href="{}" class="linkMare"><span class="den_articol">{}</span></a></span></td>'
  57.         span = re.findall(span_pattern, articol_categorie)
  58.         lista_span_nou = list()
  59.         for i in range(len(span)):
  60.             lista_span_nou.append(span_nou.format(span[i][0], span[i][1]))
  61.         span_pattern = re.compile('<td><span class="den_articol"><a href=\".*?\" class="linkMare">.*?</a></span></td>')
  62.         span = re.findall(span_pattern, articol_categorie)
  63.         for i in range(len(span)):
  64.             articol_categorie = articol_categorie.replace(span[i], lista_span_nou[i])
  65.         # ==== INLOCUIRE <td><span class="den_articol"> CU <td><span class="linkMare"> ====
  66.  
  67.         # ==== Informatii fisier original ====
  68.         categ_link_title_pattern = re.compile('<td><span class="linkMare"><a href="(.*?)" class="linkMare"><span class="den_articol">(.*?)</span></a></span></td>')
  69.         categ_link_title = re.findall(categ_link_title_pattern, articol_categorie)
  70.         print("Total {} ARTICOLE".format(len(categ_link_title)))
  71.         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>')
  72.         categ_date_link_title_desc = re.findall(categ_date_link_title_desc_pattern, articol_categorie)
  73.         paragraf_pattern = re.compile('<p class="text_obisnuit2"><em>(.*?)</em></p>')
  74.         paragraf = re.findall(paragraf_pattern, articol_categorie)
  75.  
  76.         # === citeste mai departe - buton ===
  77.         citeste_buton_pattern = re.compile('<div align="right" id="external2"><a href=\"(.*?)\">cite&#351;te mai departe </a>')
  78.         citeste_buton = re.findall(citeste_buton_pattern, articol_categorie)
  79.         read_more_buton_pattern = re.compile('<div align="right" id="external2"><a href=\"(.*?)\">read more </a>')
  80.         read_more_buton = re.findall(read_more_buton_pattern, articol_categorie)
  81.  
  82.         # === Informatii index2 ===
  83.         articol_categorie_index2_pattern = re.compile('<!-- ARTICOL START -->([\s\S]*?)<!-- ARTICOL FINAL -->')
  84.         articol_categorie_index2 = re.findall(articol_categorie_index2_pattern, text_html_model)
  85.         if len(articol_categorie_index2) != 0:
  86.             articol_categorie_index2 = articol_categorie_index2[0] # trebuie inlocuit cu toate categoriile din fisierul original
  87.             # citire template pentru categorie din index2.html
  88.             template_categorie = read_text_from_file("C:\\Folder1\\template_categorie.txt")
  89.  
  90.             # h3 => title + description
  91.             h3_pattern = re.compile('<h3 class="font-weight-normal" itemprop="name"><a href=\"(.*?)\" class="color-black">(.*?)</a></h3>')
  92.             h3 = re.findall(h3_pattern, template_categorie)
  93.             h3 = h3[0]
  94.             # dates section din index2.html
  95.             dates_section_index2_pattern = re.compile('<!--STARTDATES-->([\s\S]*?)<!--FINNISHDATES-->')
  96.             dates_section_index2 = re.findall(dates_section_index2_pattern, template_categorie)
  97.             dates_section_index2 = dates_section_index2[0]
  98.             date_index2_pattern = re.compile('<a href="javascript:void\(0\)" class="color-black">(.*?)</a>')
  99.             # date
  100.             date_index2 = re.findall(date_index2_pattern, dates_section_index2)
  101.             date_index2 = date_index2[0]
  102.             # link / title / description
  103.             link_title_desc_index2_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\" class="color-green font-weight-600 mx-1" id="hidden">(.*?)</a>')
  104.             link_title_desc_index2 = re.findall(link_title_desc_index2_pattern, dates_section_index2)
  105.             link_title_desc_index2 = link_title_desc_index2[0]
  106.  
  107.             # paragraf
  108.             paragraf_index2_pattern = re.compile('<p class="mb-35px color-grey line-height-25px">(.*?)</p>')
  109.             paragraf_index2 = re.findall(paragraf_index2_pattern, template_categorie)
  110.             paragraf_index2 = paragraf_index2[0]
  111.  
  112.             # === read more ===
  113.             read_more_pattern = re.compile('<a href=\"(.*?)\" class="btn-setting color-black btn-hvr-up btn-blue btn-hvr-pink">read more</a>')
  114.             read_more = re.findall(read_more_pattern, template_categorie)
  115.             read_more = read_more[0]
  116.  
  117.             butoane = list()
  118.             if len(citeste_buton) > 0:
  119.                 butoane = citeste_buton
  120.             else:
  121.                 butoane = read_more_buton
  122.  
  123.             for i in range(len(categ_link_title)):
  124.                 new_template = template_categorie
  125.                 # === facem replace cu informatiile din articolul original ===
  126.                 new_template_1 = new_template.replace(date_index2, categ_date_link_title_desc[i][0].replace(', in', '').strip())
  127.                 new_template_2 = new_template_1.replace(link_title_desc_index2[0], categ_date_link_title_desc[i][1])
  128.                 new_template_3 = new_template_2.replace(link_title_desc_index2[1], categ_date_link_title_desc[i][2])
  129.                 new_template_4 = new_template_3.replace(link_title_desc_index2[2], categ_date_link_title_desc[i][3].lstrip())
  130.                 new_template_5 = new_template_4.replace(paragraf_index2, paragraf[i])
  131.                 new_template_6 = new_template_5.replace(read_more, butoane[i])
  132.                 new_template_7 = new_template_6.replace(h3[0], categ_link_title[i][0])
  133.                 new_template_8 = new_template_7.replace(h3[1], categ_link_title[i][1])
  134.                 final_text = final_text + new_template_8 + '\n'
  135.  
  136.             text_html_model = text_html_model.replace(articol_categorie_index2, final_text)
  137.             final_text = text_html_model
  138.  
  139.             # schimbare CATEGORIES index2
  140.             # preluare lista fisier html
  141.             lista_pattern = re.compile('<ul id="sidebarNavigation">([\s\S]*?)</ul>')
  142.             lista = re.findall(lista_pattern, text_html)
  143.             if len(lista) != 0:
  144.                 lista = lista[0]
  145.                 elemente_lista_pattern = re.compile('<li><a href=\"(.*?)\" title=\"(.*?)\">(.*?) \((.*?)\)</a></li>')
  146.                 elemente_lista = re.findall(elemente_lista_pattern, lista)
  147.                 if elemente_lista != 0:
  148.                     categories_pattern = re.compile('<!-- Categories -->([\s\S]*?)<!-- BOOKS START -->')
  149.                     categories = re.findall(categories_pattern, final_text)
  150.                     if len(categories) != 0:
  151.                         categories = categories[0]
  152.                         elemente_lista_model_pattern = re.compile('<div class="categories-name">([\s\S]*?)</div>')
  153.                         elemente_lista_model = re.findall(elemente_lista_model_pattern, categories)
  154.                         template_category = read_text_from_file('C:\\Folder1\\category-name.txt')
  155.  
  156.                         for i in range(len(elemente_lista_model)):
  157.                             new_template_category = template_category
  158.                             a_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\">')
  159.                             a = re.findall(a_pattern, new_template_category)[0]
  160.                             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>')
  161.                             p = re.findall(p_pattern, new_template_category)[0]
  162.                             new_template_category = new_template_category.replace(a[0], elemente_lista[i][0])
  163.                             new_template_category = new_template_category.replace(a[1], elemente_lista[i][1])
  164.                             new_template_category = new_template_category.replace(p[0], elemente_lista[i][2])
  165.                             new_template_category = new_template_category.replace(p[1], elemente_lista[i][3])
  166.                             # print(final_text)
  167.                             final_text = final_text.replace(elemente_lista_model[i], new_template_category)
  168.  
  169.                     else:
  170.                         print("No categories + books start")
  171.                 else:
  172.                     print("Niciun element <li>.")
  173.             else:
  174.                 print("Tag <ul> gol.")
  175.  
  176.  
  177.             # Shimbare LINK-URI FLAGS
  178.             flags_pattern = re.compile('<!-- FLAGS_1 -->([\s\S]*?)<!-- FLAGS -->')
  179.             flags = re.findall(flags_pattern, text_html)
  180.             if len(flags) != 0:
  181.                 flags = flags[0]
  182.                 links_pattern = re.compile('<a href=\"(.*?)\">')
  183.                 links = re.findall(links_pattern, flags)
  184.                 if len(links) != 0:
  185.                     # print("Links: ", links)
  186.                     flags_model = re.findall(flags_pattern, final_text)
  187.                     if len(flags_model) != 0:
  188.                         flags_model = flags_model[0]
  189.                         links_pattern_model = re.compile('<li><a cunt_code=\"\+\d+\" href=\"(.*?)\">')
  190.                         links_model = re.findall(links_pattern_model, flags_model)
  191.                         if len(links_model) != 0:
  192.                             for i in range(len(links)):
  193.                                 # print(links[i], links_model[i])
  194.                                 final_text = final_text.replace(links_model[i], links[i]) # FACE REPLACE
  195.                         else:
  196.                             print("Fara links in flags model")
  197.                     else:
  198.                         print("Fara links in flags model")
  199.                 else:
  200.                     print("Fara linkuri in flags.")
  201.             else:
  202.                 print("Fara flags in articol original.")
  203.  
  204.             # STARS - PHP
  205.             stars_php_pattern = re.compile('\$item_id = (.*?);')
  206.             stars_php = re.findall(stars_php_pattern, text_html)
  207.             stars_php_model = re.findall(stars_php_pattern, final_text)
  208.             if len(stars_php) != 0:
  209.                 stars_php = stars_php[0]
  210.                 if len(stars_php_model) != 0:
  211.                     stars_php_model = stars_php_model[0]
  212.                     final_text = final_text.replace(stars_php_model, stars_php) # FACE REPLACE
  213.                 else:
  214.                     print("No stars fisier model")
  215.             else:
  216.                 print("No stars fisier original")
  217.  
  218.              # TITLE
  219.             title_pattern = re.compile('<title>(.*?)</title>')
  220.             text_title = re.findall(title_pattern, text_html)
  221.             text_title_model = re.findall(title_pattern, final_text)
  222.             if len(text_title) != 0 and len(text_title_model) != 0:
  223.                 text_title = text_title[0]
  224.                 text_title_model = text_title_model[0]
  225.                 final_text = final_text.replace(text_title_model, text_title)
  226.             else:
  227.                 print("Fisier html fara tag title: {}".format(cale_fisier_html))
  228.  
  229.             # DESCRIPTION
  230.             description_pattern = re.compile('<meta name="description" content="(.*?)">')
  231.             text_description = re.findall(description_pattern, text_html)
  232.             text_description_model = re.findall(description_pattern, final_text)
  233.             if len(text_description) != 0 and len(text_description_model) != 0:
  234.                 text_description = text_description[0]
  235.                 text_description_model = text_description_model[0]
  236.                 final_text = final_text.replace(text_description_model, text_description)
  237.             else:
  238.                 print("Fisier html fara tag description: {}".format(cale_fisier_html))
  239.  
  240.             # CANONICAL
  241.             canonical_pattern = re.compile('<link rel="canonical" href="(.*?)" />')
  242.             text_canonical = re.findall(canonical_pattern, text_html)
  243.             text_canonical_model = re.findall(canonical_pattern, final_text)
  244.             if len(text_canonical) != 0 and len(text_canonical_model) != 0:
  245.                 text_canonical = text_canonical[0]
  246.                 text_canonical_model = text_canonical_model[0]
  247.                 final_text = final_text.replace(text_canonical_model, text_canonical)
  248.             else:
  249.                 print("Fisier html fara tag canonical: {}".format(cale_fisier_html))
  250.  
  251.             # ULTIMELE ARTICOLE
  252.             ult_art_pattern = re.compile('<!-- Ultimele articole -->([\s\S]*?)<!-- Ultimele articole final -->')
  253.             ult_art_model_pattern = re.compile('<!-- Recent Post -->([\s\S]*?)<!-- Categories -->')
  254.             ult_art = re.findall(ult_art_pattern, text_html)
  255.             ult_art_model = re.findall(ult_art_model_pattern, final_text)
  256.             if len(ult_art) != 0:
  257.                 ult_art = ult_art[0]
  258.                 if len(ult_art_model) != 0:
  259.                     ult_art_model = ult_art_model[0]
  260.                     articole_pattern = re.compile('<li><a href=\"(.*?)\">(.*?)</a></li>')
  261.                     articole = re.findall(articole_pattern, ult_art)
  262.                     if len(articole) != 0:
  263.                         articole_model_pattern = re.compile('<a href=\"(.*?)\" class="color-grey">(.*?)</a>')
  264.                         articole_model = re.findall(articole_model_pattern, ult_art_model)
  265.                         if len(articole_model) != 0:
  266.                             for i in range(len(articole)):
  267.                                 # href - 0 / description - 1
  268.                                 final_text = final_text.replace(articole_model[i][0], articole[i][0])
  269.                                 final_text = final_text.replace(articole_model[i][1], articole[i][1])
  270.                         else:
  271.                             print("No articole fisier model")
  272.                     else:
  273.                         print("No articole fisier original")
  274.                 else:
  275.                     print("No lista articole fisier model")
  276.             else:
  277.                 print("No lista articole fisier original")
  278.  
  279.         else:
  280.             print("Nu exista articol categorie in index2.html")
  281.     else:
  282.         # === citire fisier model - index.html ===
  283.         text_html_model = read_text_from_file("C:\\Folder1\\index.html")
  284.         # ARTICOL START - FINAL
  285.         articol_pattern = re.compile('<!-- ARTICOL START -->([\s\S]*?)<!-- ARTICOL FINAL -->[\s\S]*?')
  286.         text_articol = re.findall(articol_pattern, text_html)
  287.         text_articol_model = re.findall(articol_pattern, text_html_model)
  288.         if len(text_articol) != 0 and len(text_articol_model) != 0:
  289.             text_articol = text_articol[0]
  290.             text_articol_model = text_articol_model[0]
  291.             text_html_model_1 = text_html_model.replace(text_articol_model, text_articol)
  292.             final_text = text_html_model_1
  293.         else:
  294.             print("Fisier html fara ARTICOL START/FINAL: {}".format(cale_fisier_html))
  295.  
  296.         # TITLE
  297.         title_pattern = re.compile('<title>(.*?)</title>')
  298.         text_title = re.findall(title_pattern, text_html)
  299.         text_title_model = re.findall(title_pattern, text_html_model_1)
  300.         if len(text_title) != 0 and len(text_title_model) != 0:
  301.             text_title = text_title[0]
  302.             text_title_model = text_title_model[0]
  303.             text_html_model_2 = text_html_model_1.replace(text_title_model, text_title)
  304.             final_text = text_html_model_2
  305.         else:
  306.             print("Fisier html fara tag title: {}".format(cale_fisier_html))
  307.  
  308.         # DESCRIPTION
  309.         description_pattern = re.compile('<meta name="description" content="(.*?)">')
  310.         text_description = re.findall(description_pattern, text_html)
  311.         text_description_model = re.findall(description_pattern, text_html_model_2)
  312.         if len(text_description) != 0 and len(text_description_model) != 0:
  313.             text_description = text_description[0]
  314.             text_description_model = text_description_model[0]
  315.             text_html_model_3 = text_html_model_2.replace(text_description_model, text_description)
  316.             final_text = text_html_model_3
  317.         else:
  318.             print("Fisier html fara tag description: {}".format(cale_fisier_html))
  319.  
  320.         # CANONICAL
  321.         canonical_pattern = re.compile('<link rel="canonical" href="(.*?)" />')
  322.         text_canonical = re.findall(canonical_pattern, text_html)
  323.         text_canonical_model = re.findall(canonical_pattern, text_html_model_3)
  324.         if len(text_canonical) != 0 and len(text_canonical_model) != 0:
  325.             text_canonical = text_canonical[0]
  326.             text_canonical_model = text_canonical_model[0]
  327.             text_html_model_4 = text_html_model_3.replace(text_canonical_model, text_canonical)
  328.             final_text = text_html_model_4
  329.         else:
  330.             print("Fisier html fara tag canonical: {}".format(cale_fisier_html))
  331.  
  332.  
  333.         # remove DIV tag and TABLE tag
  334.         text_articol_model = re.findall(articol_pattern, text_html_model_4)
  335.         text_articol_model_old = text_articol_model[0]
  336.         text_articol_model = text_articol_model[0]
  337.         text_articol_model = text_articol_model.replace("<div align=\"justify\">", '')
  338.         text_articol_model = text_articol_model.replace("</div>", '')
  339.  
  340.         table_pattern = re.compile('<table[\s\S]*?</table>')
  341.         text_table = re.findall(table_pattern, text_articol_model)
  342.         if len(text_table) != 0:
  343.             text_table = text_table[0]
  344.             text_articol_model = text_articol_model.replace(text_table, '')
  345.             text_html_model_5 = text_html_model_4.replace(text_articol_model_old, text_articol_model)
  346.             final_text = text_html_model_5
  347.         else:
  348.             print("No text table")
  349.  
  350.         # schimbare tag-uri ARTICLE TITLE
  351.         article_title_pattern = re.compile('<h1 class="den_articol" itemprop="name">(.*?)</h1>')
  352.         article_title = re.findall(article_title_pattern, text_articol_model_old)
  353.         if len(article_title) != 0:
  354.             article_title = article_title[0]
  355.             h3_title_pattern = re.compile('<h3 class="font-weight-normal" itemprop="name"><a href="javascript:void\(0\)" class="color-black">(.*?)</a></h3>')
  356.             h3_title = re.findall(h3_title_pattern, text_html_model_5)
  357.             if len(h3_title) != 0:
  358.                 h3_title = h3_title[0]
  359.                 text_html_model_6 = text_html_model_5.replace(h3_title, article_title)
  360.                 final_text = text_html_model_6
  361.             else:
  362.                 print("No h3 title.")
  363.         else:
  364.             print("No article title.")
  365.  
  366.         # schimbare DATE
  367.         date_pattern = re.compile('<td class="text_dreapta">(.*?), in <a')
  368.         date = re.findall(date_pattern, text_articol_model_old)
  369.         if len(date) != 0:
  370.             date = date[0]
  371.             # MODIFICARE 09/03
  372.             date_section_pattern = re.compile('<!--STARTDATES-->([\s\S]*?)<!--FINNISHDATES-->')
  373.             date_section = re.findall(date_section_pattern, text_html_model_6)
  374.             if len(date_section) > 0:
  375.                 date_section = date_section[0]
  376.                 date_pattern_model = re.compile('<a href="javascript:void\(0\)" class="color-black">(.*?)</a>')
  377.                 date_model = re.findall(date_pattern_model, date_section)
  378.                 if len(date_model) != 0:
  379.                     date_model = date_model[0]
  380.                     text_html_model_7 = text_html_model_6.replace(date_model, date)
  381.                     final_text = text_html_model_7
  382.                 else:
  383.                     print('No date in model.')
  384.             else:
  385.                 print("No date section: <!--STARTDATES--><!--FINNISHDATES-->")
  386.         else:
  387.             print("No date.")
  388.  
  389.         # schimbare SECTION
  390.         section_pattern_model = re.compile('<a href=\"(.*?)\" title=\"(.*?)\" class="color-green font-weight-600 mx-1" id="hidden">(.*?)</a>')
  391.         section_model = re.findall(section_pattern_model, text_html_model_7)
  392.         # print(section_model)
  393.         if len(section_model) != 0:
  394.             section_model = section_model[0]
  395.             section_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\" class="external" rel="category tag">(.*?)</a>')
  396.             section = re.findall(section_pattern, text_articol_model_old)
  397.             if len(section) != 0:
  398.                 section = section[0]
  399.                 text_html_model_8 = text_html_model_7.replace(section_model[0], section[0])
  400.                 text_html_model_9 = text_html_model_8.replace(section_model[1], section[1])
  401.                 text_html_model_10 = text_html_model_9.replace(section_model[2], section[2])
  402.                 final_text = text_html_model_10
  403.             else:
  404.                 print("No section.")
  405.         else:
  406.             print("No section model.")
  407.  
  408.         # schimbare CATEGORIES
  409.         # preluare lista fisier html
  410.         lista_pattern = re.compile('<ul id="sidebarNavigation">([\s\S]*?)</ul>')
  411.         lista = re.findall(lista_pattern, text_html)
  412.         if len(lista) != 0:
  413.             lista = lista[0]
  414.             elemente_lista_pattern = re.compile('<li><a href=\"(.*?)\" title=\"(.*?)\">(.*?) \((.*?)\)</a></li>')
  415.             elemente_lista = re.findall(elemente_lista_pattern, lista)
  416.             if elemente_lista != 0:
  417.                 categories_pattern = re.compile('<!-- Categories -->([\s\S]*?)<!-- BOOKS START -->')
  418.                 categories = re.findall(categories_pattern, text_html_model_10)
  419.                 if len(categories) != 0:
  420.                     categories = categories[0]
  421.                     elemente_lista_model_pattern = re.compile('<div class="categories-name">([\s\S]*?)</div>')
  422.                     elemente_lista_model = re.findall(elemente_lista_model_pattern, categories)
  423.                     template_category = read_text_from_file('C:\\Folder1\\category-name.txt')
  424.  
  425.                     for i in range(len(elemente_lista_model)):
  426.                         new_template_category = template_category
  427.                         a_pattern = re.compile('<a href=\"(.*?)\" title=\"(.*?)\">')
  428.                         a = re.findall(a_pattern, new_template_category)[0]
  429.                         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>')
  430.                         p = re.findall(p_pattern, new_template_category)[0]
  431.                         new_template_category = new_template_category.replace(a[0], elemente_lista[i][0])
  432.                         new_template_category = new_template_category.replace(a[1], elemente_lista[i][1])
  433.                         new_template_category = new_template_category.replace(p[0], elemente_lista[i][2])
  434.                         new_template_category = new_template_category.replace(p[1], elemente_lista[i][3])
  435.                         # print(final_text)
  436.                         final_text = final_text.replace(elemente_lista_model[i], new_template_category)
  437.                         # print("==========================")
  438.                         # print(final_text)
  439.                     text_html_model_14 = final_text
  440.                 else:
  441.                     print("No categories + books start")
  442.             else:
  443.                 print("Niciun element <li>.")
  444.         else:
  445.             print("Tag <ul> gol.")
  446.  
  447.         # Shimbare LINK-URI FLAGS
  448.         flags_pattern = re.compile('<!-- FLAGS_1 -->([\s\S]*?)<!-- FLAGS -->')
  449.         flags = re.findall(flags_pattern, text_html)
  450.         if len(flags) != 0:
  451.             flags = flags[0]
  452.             links_pattern = re.compile('<a href=\"(.*?)\">')
  453.             links = re.findall(links_pattern, flags)
  454.             if len(links) != 0:
  455.                 # print("Links: ", links)
  456.                 flags_model = re.findall(flags_pattern, text_html_model_14)
  457.                 if len(flags_model) != 0:
  458.                     flags_model = flags_model[0]
  459.                     # print("Flags: ", flags_model)
  460.                     links_pattern_model = re.compile('<li><a cunt_code=\"\+\d+\" href=\"(.*?)\">')
  461.                     links_model = re.findall(links_pattern_model, flags_model)
  462.                     # print(links_model)
  463.                     text_html_model_15 = text_html_model_14
  464.                     if len(links_model) != 0:
  465.                         for i in range(len(links)):
  466.                             # print(links[i], links_model[i])
  467.                             text_html_model_15 = text_html_model_15.replace(links_model[i], links[i]) # FACE REPLACE
  468.                             final_text = text_html_model_15
  469.                     else:
  470.                         print("Fara links in flags model")
  471.                 else:
  472.                     print("Fara links in flags model")
  473.             else:
  474.                 print("Fara linkuri in flags.")
  475.         else:
  476.             print("Fara flags in articol original.")
  477.  
  478.         # STARS - PHP
  479.         stars_php_pattern = re.compile('\$item_id = (.*?);')
  480.         stars_php = re.findall(stars_php_pattern, text_html)
  481.         stars_php_model = re.findall(stars_php_pattern, text_html_model_15)
  482.         if len(stars_php) != 0:
  483.             stars_php = stars_php[0]
  484.             if len(stars_php_model) != 0:
  485.                 stars_php_model = stars_php_model[0]
  486.                 text_html_model_16 = text_html_model_15.replace(stars_php_model, stars_php) # FACE REPLACE
  487.                 final_text = text_html_model_16
  488.             else:
  489.                 print("No stars fisier model")
  490.         else:
  491.             print("No stars fisier original")
  492.  
  493.         # ULTIMELE ARTICOLE
  494.         ult_art_pattern = re.compile('<!-- Ultimele articole -->([\s\S]*?)<!-- Ultimele articole final -->')
  495.         ult_art_model_pattern = re.compile('<!-- Recent Post -->([\s\S]*?)<!-- Categories -->')
  496.         ult_art = re.findall(ult_art_pattern, text_html)
  497.         ult_art_model = re.findall(ult_art_model_pattern, text_html_model_16)
  498.         if len(ult_art) != 0:
  499.             ult_art = ult_art[0]
  500.             if len(ult_art_model) != 0:
  501.                 ult_art_model = ult_art_model[0]
  502.                 articole_pattern = re.compile('<li><a href=\"(.*?)\">(.*?)</a></li>')
  503.                 articole = re.findall(articole_pattern, ult_art)
  504.                 if len(articole) != 0:
  505.                     articole_model_pattern = re.compile('<a href=\"(.*?)\" class="color-grey">(.*?)</a>')
  506.                     articole_model = re.findall(articole_model_pattern, ult_art_model)
  507.                     if len(articole_model) != 0:
  508.                         for i in range(len(articole)):
  509.                             # href - 0 / description - 1
  510.                             # MODIFICARE 09/03
  511.                             final_text = final_text.replace(articole_model[i][0], articole[i][0])
  512.                             final_text = final_text.replace(articole_model[i][1], articole[i][1])
  513.                     else:
  514.                         print("No articole fisier model")
  515.                 else:
  516.                     print("No articole fisier original")
  517.             else:
  518.                 print("No lista articole fisier model")
  519.         else:
  520.             print("No lista articole fisier original")
  521.  
  522.     file_path = cale_fisiere_gata + "\\" + os.path.basename(cale_fisier_html)
  523.     write_to_file(final_text, file_path)
  524.     print("Scriere efectuata cu succes.")
  525.  
  526.  
  527.  
  528. def creare_fisiere_html(cale_folder_html, cale_fisiere_gata):
  529.     """
  530.    Functia itereaza printr-un folder care contine fisiere txt si creeaza fisiere html corespunzatoare
  531.    """
  532.     count = 0
  533.     for f in os.listdir(cale_folder_html):
  534.             if f.endswith('.html'):
  535.                 cale_fisier_html = cale_folder_html + "\\" + f
  536.                 print("FISIER CURENT: ", cale_fisier_html)
  537.                 copiaza_continut_html(cale_fisier_html, cale_fisiere_gata)
  538.                 count += 1
  539.             else:
  540.                 continue
  541.     print("Numarul de fisiere modificate: ", count)
  542.  
  543. def main():
  544.     creare_fisiere_html("C:\\Folder1\\fisiere_html", "C:\\Folder1\\fisiere_gata")
  545.  
  546. if __name__ == '__main__':
  547.     main()
  548.  
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!