如何使用Python和Regex创建批处理处理器来替换HTML标记（解析）

   

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


 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."/>

可选的。 这是一个正则表达式表达式，它将在HTML页面中更改“关键字”标记，在每个单词后添加逗号。

使用Notepad ++ - > Ctr + F - >检查：正则表达式

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

您可以尝试此复杂版本的代码，这需要更多：从', 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": "如何使用Python和Regex创建批处理处理器来替换HTML标记（解析）| 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('] meta_description = re.search('] 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": "如何使用Python和Regex创建批处理处理器来替换HTML标记（解析）| 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('', 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)