So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags zu ersetzen (Parsing)

Name: So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen Neculai Fantanaru.
Brand: Neculai Fantanaru
SKU: NFL
Availability: OnlineOnly
Rating: 5 (55 reviews)

On Iunie 16, 2021, in Leadership and Attitude, by Neculai Fantanaru

Sie können hier den vollständigen Code ansehen:Https: // passin.com / i num5q ist 5

Ein Codebeispiel für HTML-Seiten, die mit Python-Code geändert werden. Kopieren Sie den obigen Text in eine .html-Datei, speichern Sie sie an den SpeicherortC: \ Ordner1

   

 xmlns="http://www.w3.org/1999/xhtml" dir="ltr" lang="ro">

So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen  Neculai Fantanaru.
 rel="canonical" href="https://MY-WEBSITE.COM" />
 name="description" content="I LOVE HTML and CSS"/>

 name="keywords" content="abordarea frontala a lucrurilor neelucidate"/>
 name="abstract" content="My laptop works just fine"/>
 name="Subject" content="I think I need a new car."/>
 property="og:url" content="https://otherwebsite.com"/>
 property="og:title" content="Nobody is here?" />
 property="og:description" content="Dance is my passion."/>

Der untenstehende PowerShell-Code kopiert den Inhalt der HTML-Tags mit den anderen Tags, indem sie die Daten analysieren. Sie müssen nur die Tags ausfüllenVier.

import requests
import re

# Path to english folder 1
english_folder1 = r"c:\Folder1"

# Path to english folder 2
english_folder2 = r"c:\Folder1"

extension_file = ".html"

use_parse_folder = True #Face folder nou daca pui True, iar daca pui False redenumeste fisierele in acelasi folder

import os

en1_directory = os.fsencode(english_folder1)
en2_directory = os.fsencode(english_folder2)

print('Going through english folder')
for file in os.listdir(en1_directory):
    filename = os.fsdecode(file)
    print(filename)
    if filename == 'y_key_e479323ce281e459.html' or filename == 'TS_4fg4_tr78.html':
        continue
    if filename.endswith(extension_file):
        with open(os.path.join(english_folder1, filename), encoding='utf-8') as html:
            html = html.read()

            try:
                with open(os.path.join(english_folder2, filename), encoding='utf-8') as en_html:
                    en_html = en_html.read()

                    if False:  # if True: will Parse also the content that starts from  to  and so on
                        try:
                            comment_body = re.search('.+', html, flags=re.DOTALL)[0]
                            en_html = re.sub('.+', comment_body, en_html, flags=re.DOTALL)
                        except:
                            pass

                        try:
                            comment_body2 = re.search('.+', html, flags=re.DOTALL)[0]
                            en_html = re.sub('.+', comment_body2, en_html, flags=re.DOTALL)
                        except:
                            pass

                        try:
                            comment_body3 = re.search('.+', html, flags=re.DOTALL)[0]
                            en_html = re.sub('.+', comment_body3, en_html, flags=re.DOTALL)
                        except:
                            pass

                    # title to meta
                    try:
                        title = re.search('So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen  Neculai Fantanaru.', html)[0]
                        title_content = re.search('>(.+)<', title)[1]
                    except:
                        pass

                    try:
                        meta_og_title = re.search('', en_html)[0]
                        new_meta_og_title = re.sub(r'content=".+"', f'content="{title_content}"', meta_og_title)
                        en_html = en_html.replace(meta_og_title, new_meta_og_title)
                    except:
                        pass

                    try:
                        meta_keywords = re.search('', en_html)[0]
                        new_meta_keywords = re.sub(r'content=".+"', f'content="{title_content}"', meta_keywords)
                        en_html = en_html.replace(meta_keywords, new_meta_keywords)
                    except:
                        pass

                    try:
                        meta_abstract = re.search('', en_html)[0]
                        new_meta_abstract = re.sub(r'content=".+"', f'content="{title_content}"', meta_abstract)
                        en_html = en_html.replace(meta_abstract, new_meta_abstract)
                    except:
                        pass

                    try:
                        meta_Subject = re.search('', en_html)[0]
                        new_meta_Subject = re.sub(r'content=".+"', f'content="{title_content}"', meta_Subject)
                        en_html = en_html.replace(meta_Subject, new_meta_Subject)
                    except:
                        pass

                    try:
                        headline = re.search('"headline":.+', en_html)[0]
                        new_headline = re.sub(r':.+', f': "{title_content}",', headline)
                        en_html = en_html.replace(headline, new_headline)
                    except:
                        pass

                    try:
                        keywords = re.search('"keywords": "So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen  Neculai Fantanaru.",
                        new_keywords = re.sub(r':.+', f': "{title_content}",', keywords)
                        en_html = en_html.replace(keywords, new_keywords)
                    except:
                        pass

                    # canonical to meta og:url and @id
                    try:
                        canonical_content = re.search('', html)[1]
                    except:
                        pass

                    try:
                        og_url = re.search('', en_html)[0]
                        new_og_url = re.sub(r'content=".+"', f'content="{canonical_content}"', og_url)
                        en_html = en_html.replace(og_url, new_og_url)
                    except:
                        pass

                    try:
                        id = re.search('"@id":.+', en_html)[0]
                        new_id = re.sub(r':.+', f': "{canonical_content}"', id)
                        en_html = en_html.replace(id, new_id)
                    except:
                        pass

                    # meta description to og:description and description
                    try:
                        meta = re.search('', html)[0]
                        meta_description = re.search('', html)[1]
                    except:
                        pass

                    try:
                        og_description = re.search('', en_html)[0]
                        new_og_description = re.sub(r'content=".+"', f'content="{meta_description}"', og_description)
                        en_html = en_html.replace(og_description, new_og_description)
                    except:
                        pass

                    try:
                        description = re.search('"description": "So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen  Neculai Fantanaru.",
                        new_description = re.sub(r':.+', f': "{meta_description}",', description)
                        en_html = en_html.replace(description, new_description)
                    except:
                        pass

                    try:
                        en_html = re.sub('', meta, en_html)
                    except:
                        pass

                    try:
                        en_html = re.sub('So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen  Neculai Fantanaru.', title, en_html)
                    except:
                        pass
            except FileNotFoundError:
                continue

        print(f'{filename} parsed')
        if use_parse_folder:
            try:
                with open(os.path.join(english_folder2+r'\parsed', 'parsed_'+filename), 'w', encoding='utf-8') as new_html:
                    new_html.write(en_html)
            except:
                os.mkdir(english_folder2+r'\parsed')
                with open(os.path.join(english_folder2+r'\parsed', 'parsed_'+filename), 'w', encoding='utf-8') as new_html:
                    new_html.write(en_html)
        else:
            with open(os.path.join(english_folder2, 'parsed_'+filename), 'w', encoding='utf-8') as html:
                html.write(en_html)

Optional. Hier ist ein Regex-Ausdruck, der das Tag "Keywords" in der HTML-Seite ändert, wobei nach jedem Wort ein Komma hinzugefügt wird.

Verwenden Sie mit Notepad ++ -> Ctr + F -> Check: Regelmäßiger Ausdruck

SEARCH: (?s)<title>.*?<\/title>.*?<meta\x20name="keywords"\x20content="\K(\w+)|\G[^\w\r\n]+(\w+)  
REPLACE BY:  ?1\l\1:,\x20\l\2

Sie können diese komplexe Version des Codes ausprobieren, was mehr: Abrufen der Daten aus dem Titel und kopieren Sie es in das Tag<meta name="keywords" content="erstellen, sie, einen, batch, prozessor, mit, python, und, regex, um, html, tags, parsing, zu, ersetzen, neculai, fantanaru"/> Sie können den Code hier sehen: <a href="https://pastebin.com/jM5zf2qS" target="_new">Https: // passatin.com / jm5 Regierung 2Qs</a> <div style="background: #ffffff; overflow:auto;width:auto;border:solid gray;border-width:.1em .1em .1em .4em;padding:.2em .6em;"> <pre style="margin: 0; line-height: 125%">import requests import re # Path to english folder 1 english_folder2 = r"c:\Folder1" extension_file = ".html" use_parse_folder = True import os en1_directory = os.fsencode(english_folder2) en2_directory = os.fsencode(english_folder2) # These connection words will be ignore when parsing data from <title> tag to <meta keywords> tag LISTA_CUVINTE_LEGATURA = [ 'in', 'la', 'unei', 'si', 'sa', 'se', 'de', 'prin', 'unde', 'care', 'a', 'al', 'prea', 'lui', 'din', 'ai', 'unui', 'acei', 'un', 'doar', 'tine', 'ale', 'sau', 'dintre', 'intre', 'cu','ce', 'va', 'fi', 'este', 'cand', 'o', 'cine', 'aceasta', 'ca', 'dar', 'II', 'III', 'IV', 'V', 'VI', 'VII', 'VIII', 'to', 'was', 'your', 'you', 'is', 'are', 'iar', 'fara', 'aceasta', 'pe', 'tu', 'nu', 'mai', 'ne', 'le', 'intr', 'cum', 'e', 'for', 'she', 'it', 'esti', 'this', 'that', 'how', 'can', 't', 'must', 'be', 'the', 'and', 'do', 'so', 'or', 'ori', 'who', 'what', 'if', 'of', 'on', 'i', 'we', 'they', 'them', 'but', 'where', 'by', 'an', 'on', '1', '2', '3', '4', '5', '6', '7', '8', '9', '0', 'made', 'make', 'my', 'me', '-', 'vom', 'voi', 'ei', 'cat', 'ar', 'putea', 'poti', 'sunteti', 'inca', 'still', 'noi', 'l', 'ma', 's', 'dupa', 'after', 'under', 'sub', 'niste', 'some', 'those', 'he' ] def creeaza_lista_keywords(titlu): # imparte titlul in 2 in functie de bara verticala | prima_parte_titlu = titlu.split('|')[0] # extrage toate cuvintele din prima parte a titlului keywords = re.findall(r'(?:\w|-*\!)+', prima_parte_titlu) # extrage keyword-urile care nu se gasesc in lista de cuvinte de legatura keywords_OK = list() for keyword in keywords: if keyword not in LISTA_CUVINTE_LEGATURA: # adauga keyword-ul cu litere mici keywords_OK.append(keyword.lower()) # returneaza un string in care toate keyword-urile sunt alaturate prin ', ' return ", ".join(keywords_OK) print('Going through english folder') amount = 1 for file in os.listdir(en1_directory): filename = os.fsdecode(file) print(filename) if filename == 'y_key_e479323ce281e459.html' or filename == 'directory.html': continue if filename.endswith(extension_file): with open(os.path.join(english_folder2, filename), encoding='utf-8') as html: html = html.read() try: with open(os.path.join(english_folder2, filename), encoding='utf-8') as en_html: en_html = en_html.read() # title to meta try: title = re.search('<title>So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen Neculai Fantanaru.', html)[0] title_content = re.search('>(.+)<', title)[1] except: pass try: meta_og_title = re.search('', en_html)[0] new_meta_og_title = re.sub(r'content=".+"', f'content="{title_content}"', meta_og_title) en_html = en_html.replace(meta_og_title, new_meta_og_title) except: pass try: meta_keywords = re.search('', en_html)[0] keywords = creeaza_lista_keywords(title_content) new_meta_keywords = re.sub(r'content=".+"', f'content="{keywords}"', meta_keywords) en_html = en_html.replace(meta_keywords, new_meta_keywords) except: pass try: meta_abstract = re.search('', en_html)[0] new_meta_abstract = re.sub(r'content=".+"', f'content="{title_content}"', meta_abstract) en_html = en_html.replace(meta_abstract, new_meta_abstract) except: pass try: meta_Subject = re.search('', en_html)[0] new_meta_Subject = re.sub(r'content=".+"', f'content="{title_content}"', meta_Subject) en_html = en_html.replace(meta_Subject, new_meta_Subject) except: pass try: headline = re.search('"headline":.+', en_html)[0] new_headline = re.sub(r':.+', f': "{title_content}",', headline) en_html = en_html.replace(headline, new_headline) except: pass try: keywords = re.search('"keywords": "So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen Neculai Fantanaru.", new_keywords = re.sub(r':.+', f': "{title_content}",', keywords) en_html = en_html.replace(keywords, new_keywords) except: pass # canonical to meta og:url and @id try: canonical_content = re.search('', html)[1] except: pass try: og_url = re.search('', en_html)[0] new_og_url = re.sub(r'content=".+"', f'content="{canonical_content}"', og_url) en_html = en_html.replace(og_url, new_og_url) except: pass try: id = re.search('"@id":.+', en_html)[0] new_id = re.sub(r':.+', f': "{canonical_content}"', id) en_html = en_html.replace(id, new_id) except: pass # meta description to og:description and description try: meta = re.search('', html)[0] meta_description = re.search('', html)[1] except: pass try: og_description = re.search('', en_html)[0] new_og_description = re.sub(r'content=".+"', f'content="{meta_description}"', og_description) en_html = en_html.replace(og_description, new_og_description) except: pass try: description = re.search('"description": "So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen Neculai Fantanaru.", new_description = re.sub(r':.+', f': "{meta_description}",', description) en_html = en_html.replace(description, new_description) except: pass try: en_html = re.sub('', meta, en_html) except: pass try: en_html = re.sub('So erstellen Sie einen Batch-Prozessor mit Python und Regex, um HTML-Tags (Parsing) zu ersetzen Neculai Fantanaru.', title, en_html) except: pass except FileNotFoundError: continue print(f'{filename} parsed ({amount})') amount += 1 if use_parse_folder: try: with open(os.path.join(english_folder2+r'', ''+filename), 'w', encoding='utf-8') as new_html: new_html.write(en_html) except: os.mkdir(english_folder2+r'') with open(os.path.join(english_folder2+r'', ''+filename), 'w', encoding='utf-8') as new_html: new_html.write(en_html) else: with open(os.path.join(english_folder2, 'parsed_'+filename), 'w', encoding='utf-8') as html: html.write(en_html)

That's all folks.

If you like my code, please SHARE IT

Sie können die Code-Version auch in anzeigenPower Shelloder anderer Python Version 3.oderVersion 4.oderVersion 5.

Donate via Paypal

RECURRENT DONATION

Donate monthly to support
the NeculaiFantanaru.com project

SINGLE DONATION

Donate the desired amount to support
the NeculaiFantanaru.com project

Donate by Bank Transfer

Account Ron: RO34INGB0000999900448439

Open account at ING Bank

* Note: If you want to read all my articles in real time, please check the romanian version !