convert_articles RO in docx si in pdf 2026

convert_articles RO in docx si in pdf 2026.py

from fpdf import FPDF, HTMLMixin
from docx import Document
from docx.shared import Pt, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml.ns import qn
from docx.oxml import OxmlElement
import copy
import os
import re
from PyPDF2 import PdfMerger

# pip uninstall --yes pypdf && pip install --upgrade fpdf2
# pip install python-docx

def read_text_from_file(file_path):
    with open(file_path, encoding='utf8', errors='ignore') as f:
        text = f.read()
        f.close()
        return text

def write_to_file(text, file_path):
    with open(file_path, 'wb') as f:
        f.write(text.encode('utf8', 'ignore'))
        f.close()

dict_simboluri = {
    'ă': 'ă', 'â': 'â', 'ã': 'ã', 'â': 'â', 'ă': 'ă', 'â': 'a', '  ': ' ', 'î': 'î',
    'Î': 'Î', 'î': 'î', 'î': 'î', 'Î': 'Î', 'Î': 'Î', ' ': ' ', 'ș': 'ș', 'Ș': 'Ș',
    'Ş': 'Ş', 'ș': 'ș', 'ş': 'ș', '&': '', 'ț': 'ț', 'ţ': 'ț', 'Ţ': 'Ţ', 'ț': 'ț',
    '”': '"', '“': '"'
}

def fix_html(content):
    content = re.sub(r'</span>(\s*)<p', r'</span>\1</p><p', content)
    return content

def html_to_docx_paragraph(doc, html_content, bold_paragraph=False):
    """Convert HTML content with inline tags to a docx paragraph with formatting."""
    paragraph = doc.add_paragraph()

    # Remove img tags
    html_content = re.sub('<img[^>]*>', '', html_content)

    # Split by inline formatting tags
    pattern = r'(<b>.*?</b>|<strong>.*?</strong>|<i>.*?</i>|<em>.*?</em>|<span[^>]*>.*?</span>|<a[^>]*>.*?</a>)'
    parts = re.split(pattern, html_content, flags=re.DOTALL)

    for part in parts:
        if not part:
            continue

        is_bold = bold_paragraph
        is_italic = False
        text = part

        if re.match(r'<b>', part) or re.match(r'<strong>', part):
            is_bold = True
            text = re.sub(r'</?b>|</?strong>', '', part)
        elif re.match(r'<i>', part) or re.match(r'<em>', part):
            is_italic = True
            text = re.sub(r'</?i>|</?em>', '', part)
        elif re.match(r'<span', part):
            if 'text_obisnuit2' in part:
                is_bold = True
            text = re.sub(r'<span[^>]*>|</span>', '', part)
        elif re.match(r'<a', part):
            text = re.sub(r'<a[^>]*>|</a>', '', part)

        # Strip any remaining HTML tags
        text = re.sub('<[^>]+>', '', text)

        if text:
            run = paragraph.add_run(text)
            run.bold = is_bold
            run.italic = is_italic
            run.font.size = Pt(12)

    paragraph.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
    return paragraph

def save_to_pdf(directory_path):
    modified_files = []
    file_count = 0
    for root, dirs, files in os.walk(directory_path):
        for file_name in files:
            if file_name.endswith(".html"):
                try:
                    if "webinar" in file_name:
                        print(f"Fișierul {file_name} conține 'webinar' în numele său și va fi ignorat.")
                        continue

                    file_path = root + os.sep + file_name
                    file_content = read_text_from_file(file_path)

                    if "https://pastebin.com" in file_content:
                        print(f"Fișierul {file_name} conține 'https://pastebin.com' în conținutul său și va fi ignorat.")
                        continue

                    file_content = fix_html(file_content)

                    class PDF(FPDF, HTMLMixin):
                        pass

                    if '<!-- ARTICOL START -->' in file_content:
                        pdf = PDF()
                        pdf.add_page()
                        pdf.add_font("Kanit", fname="e:/Carte/BB/17 - Site Leadership/alte/Ionel Balauta/Aryeht/Task 1 - Traduce tot site-ul/Doar Google Web/Andreea/Meditatii/Sedinta 20 august 2022/fonts/Kanit-Regular.ttf", uni=True)
                        pdf.add_font("Kanit", style="B", fname="e:/Carte/BB/17 - Site Leadership/alte/Ionel Balauta/Aryeht/Task 1 - Traduce tot site-ul/Doar Google Web/Andreea/Meditatii/Sedinta 20 august 2022/fonts/Kanit-Bold.ttf", uni=True)
                        pdf.add_font("Kanit", style="I", fname="e:/Carte/BB/17 - Site Leadership/alte/Ionel Balauta/Aryeht/Task 1 - Traduce tot site-ul/Doar Google Web/Andreea/Meditatii/Sedinta 20 august 2022/fonts/Kanit-Italic.ttf", uni=True)
                        pdf.add_font("Kanit", style="BI", fname="e:/Carte/BB/17 - Site Leadership/alte/Ionel Balauta/Aryeht/Task 1 - Traduce tot site-ul/Doar Google Web/Andreea/Meditatii/Sedinta 20 august 2022/fonts/Kanit-BoldItalic.ttf", uni=True)

                        pdf.set_font("Kanit", size=24)

                        den_articol = re.search('<h1 class="den_articol" itemprop="name">(.*?)</h1>', file_content)
                        if den_articol is None:
                            print("Nu am gasit --- denumire articol --- in fisierul --- {} ---.".format(file_path))
                        else:
                            den_articol = den_articol.group(1)
                            for simbol in dict_simboluri.keys():
                                den_articol = den_articol.replace(simbol, dict_simboluri[simbol])

                        pdf.set_text_color(204, 0, 0)
                        pdf.set_font('Kanit', size=14, style="B")
                        pdf.multi_cell(w=190, txt=den_articol, align='J')
                        pdf.ln()
                        pdf.set_font('Kanit', size=12)

                        date = re.search('<td class="text_dreapta">(.*?), in <a', file_content)
                        if date is None:
                            print("Nu am gasit --- date --- in fisierul --- {} ---.".format(file_path))
                        else:
                            date = date.group(1)

                        pdf.set_text_color(0, 102, 204)
                        pdf.set_font('Kanit', size=8, style="B")
                        pdf.cell(txt=date)
                        pdf.ln()
                        pdf.ln()
                        pdf.ln()
                        pdf.ln()
                        pdf.set_text_color(0, 0, 0)
                        pdf.set_font('Kanit', size=12)

                        articol = re.search(r'<!-- ARTICOL START -->([\s\S]*?)<!-- ARTICOL FINAL -->', file_content)

                        if articol is None:
                            print("Nu am gasit --- ARTICOL START/FINAL --- in fisierul --- {} ---.".format(file_path))
                        else:
                            articol = articol.group(1)
                            articol = articol.replace("&quot;", "\"")
                            articol = articol.replace("&rsquo;", "'")

                            par_regex = re.compile(r'<p class="text_obisnuit.*?">.*?</p>')
                            pars = re.findall(par_regex, articol)
                            pars_text = list()

                            if len(pars) == 0:
                                print("Nu am gasit -- paragrafe text_obisnuit -- in fisierul --- {} ---.".format(file_path))
                            else:
                                for i in range(0, len(pars)):
                                    if '<p class="text_obisnuit">' in pars[i]:
                                        content = re.findall('<p class="text_obisnuit">(.*?)</p>', pars[i])
                                        if len(content) == 0:
                                            print("Nu am gasit text in paragraful {}, fisierul {}.".format(pars[i], file_path))
                                        else:
                                            for simbol in dict_simboluri.keys():
                                                content[0] = content[0].replace(simbol, dict_simboluri[simbol])
                                            content[0] = re.sub('<img[^>]*>', '', content[0])
                                            content[0] = re.sub('<[^>]+>', '', content[0])
                                            content[0] = ' '.join(content[0].split())
                                            pdf.set_font('Kanit', size=12)
                                            pdf.multi_cell(w=190, txt=content[0], align='J')
                                            pdf.ln()

                                    elif '<p class="text_obisnuit2">' in pars[i]:
                                        content = re.findall('<p class="text_obisnuit2">(.*?)</p>', pars[i])
                                        if len(content) == 0:
                                            print("Nu am gasit text in paragraful {}, fisierul {}.".format(pars[i], file_path))
                                        else:
                                            for simbol in dict_simboluri.keys():
                                                content[0] = content[0].replace(simbol, dict_simboluri[simbol])
                                            content[0] = re.sub('<[^>]+>', '', content[0])
                                            content[0] = ' '.join(content[0].split())
                                            pdf.set_font('Kanit', size=12, style='B')
                                            pdf.multi_cell(w=190, txt=content[0], align='J')
                                            pdf.ln()
                                            pdf.set_font('Kanit', size=12)

                            pdf.ln()
                            pdf.ln()
                            pdf.set_font('Kanit', size=12, style="B")
                            pdf.cell(txt="Source:")
                            pdf.set_font('Kanit', size=12)
                            pdf.set_text_color(0, 102, 204)
                            pdf.cell(w=40, txt="https://neculaifantanaru.com/{}".format(file_name), link="https://neculaifantanaru.com/{}".format(file_name))
                            # pdf.cell(w=40, txt="https://neculaifantanaru.com/en/{}".format(file_name), link="https://neculaifantanaru.com/en/{}".format(file_name))

                            den_fisier = file_path.split('.')[0] + '.pdf'
                            pdf.output(den_fisier)

                    modified_files.append(file_name)
                    file_count += 1
                    print(f"Fișierul {file_count}: {file_name} a fost modificat.")

                except Exception as e:
                    print(f"Eroare la procesarea fișierului {file_name}: {e}")
                    continue

    print(f"\nAu fost modificate {file_count} fișiere:")
    for i, file_name in enumerate(modified_files, 1):
        print(f"{i}. {file_name}")

def save_to_docx(directory_path):
    modified_files = []
    file_count = 0
    for root, dirs, files in os.walk(directory_path):
        for file_name in files:
            if file_name.endswith(".html"):
                try:
                    if "webinar" in file_name:
                        print(f"Fișierul {file_name} conține 'webinar' în numele său și va fi ignorat (DOCX).")
                        continue

                    file_path = root + os.sep + file_name
                    file_content = read_text_from_file(file_path)

                    if "https://pastebin.com" in file_content:
                        print(f"Fișierul {file_name} conține 'https://pastebin.com' în conținutul său și va fi ignorat (DOCX).")
                        continue

                    file_content = fix_html(file_content)

                    if '<!-- ARTICOL START -->' in file_content:
                        doc = Document()

                        # Title
                        den_articol = re.search('<h1 class="den_articol" itemprop="name">(.*?)</h1>', file_content)
                        if den_articol is None:
                            print("Nu am gasit --- denumire articol --- in fisierul --- {} --- (DOCX).".format(file_path))
                            title_text = ""
                        else:
                            title_text = den_articol.group(1)
                            for simbol in dict_simboluri.keys():
                                title_text = title_text.replace(simbol, dict_simboluri[simbol])
                            title_text = re.sub('<[^>]+>', '', title_text)

                        title_para = doc.add_paragraph()
                        title_para.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
                        title_run = title_para.add_run(title_text)
                        title_run.bold = True
                        title_run.font.size = Pt(14)
                        title_run.font.color.rgb = RGBColor(204, 0, 0)

                        # Date
                        date = re.search('<td class="text_dreapta">(.*?), in <a', file_content)
                        if date is None:
                            print("Nu am gasit --- date --- in fisierul --- {} --- (DOCX).".format(file_path))
                        else:
                            date_text = date.group(1)
                            date_para = doc.add_paragraph()
                            date_para.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
                            date_run = date_para.add_run(date_text)
                            date_run.bold = True
                            date_run.font.size = Pt(8)
                            date_run.font.color.rgb = RGBColor(0, 102, 204)

                        doc.add_paragraph()  # spacing

                        # Article content
                        articol = re.search(r'<!-- ARTICOL START -->([\s\S]*?)<!-- ARTICOL FINAL -->', file_content)
                        if articol is None:
                            print("Nu am gasit --- ARTICOL START/FINAL --- in fisierul --- {} --- (DOCX).".format(file_path))
                        else:
                            articol = articol.group(1)
                            articol = articol.replace("&quot;", "\"")
                            articol = articol.replace("&rsquo;", "'")

                            par_regex = re.compile(r'<p class="text_obisnuit.*?">.*?</p>')
                            pars = re.findall(par_regex, articol)

                            if len(pars) == 0:
                                print("Nu am gasit -- paragrafe text_obisnuit -- in fisierul --- {} --- (DOCX).".format(file_path))
                            else:
                                for par in pars:
                                    if '<p class="text_obisnuit">' in par:
                                        content = re.findall('<p class="text_obisnuit">(.*?)</p>', par)
                                        if content:
                                            text = content[0]
                                            for simbol in dict_simboluri.keys():
                                                text = text.replace(simbol, dict_simboluri[simbol])
                                            html_to_docx_paragraph(doc, text, bold_paragraph=False)

                                    elif '<p class="text_obisnuit2">' in par:
                                        content = re.findall('<p class="text_obisnuit2">(.*?)</p>', par)
                                        if content:
                                            text = content[0]
                                            for simbol in dict_simboluri.keys():
                                                text = text.replace(simbol, dict_simboluri[simbol])
                                            html_to_docx_paragraph(doc, text, bold_paragraph=True)

                        # Source
                        doc.add_paragraph()
                        source_para = doc.add_paragraph()
                        source_para.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
                        bold_run = source_para.add_run("Source: ")
                        bold_run.bold = True
                        bold_run.font.size = Pt(12)
                        url_run = source_para.add_run("https://neculaifantanaru.com/{}".format(file_name))
                        url_run.font.size = Pt(12)
                        url_run.font.color.rgb = RGBColor(0, 102, 204)

                        den_fisier_docx = file_path.split('.')[0] + '.docx'
                        doc.save(den_fisier_docx)

                    modified_files.append(file_name)
                    file_count += 1
                    print(f"Fișierul DOCX {file_count}: {file_name} a fost procesat.")

                except Exception as e:
                    print(f"Eroare la procesarea DOCX fișierului {file_name}: {e}")
                    continue

    print(f"\nAu fost procesate {file_count} fișiere DOCX:")
    for i, file_name in enumerate(modified_files, 1):
        print(f"{i}. {file_name}")

def merge_pdf_files(directory_path):
    merger = PdfMerger()
    pdf_files = []

    for root, dirs, files in os.walk(directory_path):
        for file_name in files:
            if file_name.endswith(".pdf"):
                print("PDF: ", file_name)
                file_path = root + os.sep + file_name
                pdf_files.append(file_path)
                merger.append(file_path)

    output_path = root + os.sep + "articles.pdf"
    merger.write(output_path)
    merger.close()

    for pdf_file in pdf_files:
        if pdf_file != output_path:
            os.remove(pdf_file)
            print(f"Fișierul {pdf_file} a fost șters.")

def merge_docx_files(directory_path):
    master = Document()
    # Remove default empty paragraph added by python-docx
    for elem in list(master.element.body):
        master.element.body.remove(elem)

    docx_files = []
    first = True

    for root, dirs, files in os.walk(directory_path):
        for file_name in sorted(files):
            if file_name.endswith(".docx") and file_name != "articles.docx":
                print("DOCX: ", file_name)
                file_path = os.path.join(root, file_name)
                docx_files.append(file_path)

                doc = Document(file_path)

                if not first:
                    # Add page break between articles
                    p = OxmlElement('w:p')
                    r = OxmlElement('w:r')
                    br = OxmlElement('w:br')
                    br.set(qn('w:type'), 'page')
                    r.append(br)
                    p.append(r)
                    master.element.body.append(p)

                first = False

                for element in doc.element.body:
                    master.element.body.append(copy.deepcopy(element))

    output_path = os.path.join(directory_path, "articles.docx")
    master.save(output_path)
    print(f"\nFișierul articles.docx a fost salvat la: {output_path}")

    for docx_file in docx_files:
        if docx_file != output_path:
            os.remove(docx_file)
            print(f"Fișierul {docx_file} a fost șters.")

save_to_pdf("c:\\Folder9\\")
merge_pdf_files("c:\\Folder9\\")

save_to_docx("c:\\Folder9\\")
merge_docx_files("c:\\Folder9\\")