re-initialize and make some changes. repository got to around 2 gigabytes and needed to be more efficient

scripts/agebypass.py

@@ -0,0 +1,19 @@
+import os
+import re
+
+def remove_age_gate(file_path):
+    with open(file_path, 'r') as file:
+        content = file.read()
+
+    new_content = re.sub(
+        r'<script id="age_check_preload" src="https:\/\/diyhrt\.wiki\/age-check\.js">.*?<\/script>', '', content, flags=re.DOTALL)
+
+    with open(file_path, 'w') as file:
+        file.write(new_content)
+
+directory_path = 'diyhrt.wiki'
+
+for filename in os.listdir(directory_path):
+    file_path = os.path.join(directory_path, filename)
+    if os.path.isfile(file_path):
+        remove_age_gate(file_path)

scripts/cafe.txt

@@ -0,0 +1,36 @@
+https://diyhrt.cafe/index.php/Special:MyTalk
+https://diyhrt.cafe/index.php/Special:MyContributions
+https://diyhrt.cafe/index.php?title=Special:CreateAccount&returnto=Special%3AAllPages
+https://diyhrt.cafe/index.php?title=Special:UserLogin&returnto=Special%3AAllPages
+https://diyhrt.cafe/index.php/Main_Page
+https://diyhrt.cafe/index.php/Archives
+https://diyhrt.cafe/index.php/Bicalutamide
+https://diyhrt.cafe/index.php/Clomifene
+https://diyhrt.cafe/index.php/Commentary_and_Fact_Check_of_Dr._Will_Powers%E2%80%99s_Transgender_Care_Presentation@TransfemScience
+https://diyhrt.cafe/index.php/Cyproterone_Acetate
+https://diyhrt.cafe/index.php/Domperidone
+https://diyhrt.cafe/index.php/Donate
+https://diyhrt.cafe/index.php/Dutasteride
+https://diyhrt.cafe/index.php/EUAibolit_Updates
+https://diyhrt.cafe/index.php/Estradiol_Gel
+https://diyhrt.cafe/index.php/Estradiol_Injections
+https://diyhrt.cafe/index.php/Estradiol_Patches
+https://diyhrt.cafe/index.php/Estradiol_Pills
+https://diyhrt.cafe/index.php/Finasteride
+https://diyhrt.cafe/index.php/Gonadotropin-Releasing_Hormone_Agonists
+https://diyhrt.cafe/index.php/Hydroxyprogesterone_Caproate_Injections
+https://diyhrt.cafe/index.php/Main_Page/sandbox
+https://diyhrt.cafe/index.php/Pioglitazone
+https://diyhrt.cafe/index.php/Progesterone_Capsules
+https://diyhrt.cafe/index.php/Progesterone_Gel
+https://diyhrt.cafe/index.php/Progesterone_Injections
+https://diyhrt.cafe/index.php/Raloxifene
+https://diyhrt.cafe/index.php/Resources
+https://diyhrt.cafe/index.php/Sandbox
+https://diyhrt.cafe/index.php/Spironolactone
+https://diyhrt.cafe/index.php/Tamoxifen
+https://diyhrt.cafe/index.php/Special:AllPages
+https://diyhrt.cafe/index.php/Project:About
+https://diyhrt.cafe/index.php/Special:SpecialPages
+https://diyhrt.cafe/index.php/Project:Privacy_policy
+https://diyhrt.cafe/index.php/Project:General_disclaimer

scripts/formatlinks.py

@@ -0,0 +1,27 @@
+import sys
+
+def remove_trailing_spaces(line):
+    return line.rstrip()
+
+def remove_duplicate_lines(file_path):
+    lines_seen = set()
+    output_lines = []
+
+    with open(file_path, 'r') as file:
+        for line in file:
+            cleaned_line = remove_trailing_spaces(line)
+
+            if cleaned_line.startswith("https://diyhrt.cafe") and cleaned_line not in lines_seen:
+                lines_seen.add(cleaned_line)
+                output_lines.append(line)
+
+    with open(file_path, 'w') as file:
+        file.writelines(output_lines)
+
+# Usage example
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Please provide the file path as an argument.")
+    else:
+        file_path = sys.argv[1]
+        remove_duplicate_lines(file_path)

scripts/getlinks.py

@@ -0,0 +1,29 @@
+from bs4 import BeautifulSoup
+from urllib.request import Request, urlopen
+import re
+import sys
+from urllib.parse import urljoin
+
+if len(sys.argv) < 2:
+    print("Please provide a URL.")
+    sys.exit(1)
+
+url = sys.argv[1]
+
+headers = {'User-Agent': 'Mozilla/5.0'}
+
+req = Request(url, headers=headers)
+
+html_page = urlopen(req)
+
+soup = BeautifulSoup(html_page, "html.parser")
+
+links = []
+for link in soup.findAll('a'):
+    href = link.get('href')
+    if href:
+        full_url = urljoin(url, href)
+        links.append(full_url)
+
+formatted_links = '\n'.join(links)
+print(formatted_links)

scripts/make_index.py

@@ -0,0 +1,58 @@
+import os
+import argparse
+
+# May need to do "pip install mako"
+from mako.template import Template
+
+
+INDEX_TEMPLATE = r"""
+<html>
+<head>
+    <style>
+        body {
+            background-color: black;
+            color: white;
+            font-size: 25px;
+        }
+
+        a {
+            color: white;
+        }
+    </style>
+</head>
+<body>
+    <h2>${header}</h2>
+    <p>
+        % for name in names:
+            <a href="${name}">${name}</a><br>
+        % endfor
+    </p>
+</body>
+</html>
+"""
+
+EXCLUDED = ['index.html']
+
+
+def generate_index(directory):
+    fnames = [fname for fname in sorted(os.listdir(directory)) if fname not in EXCLUDED]
+    header = os.path.basename(directory)
+    index_content = Template(INDEX_TEMPLATE).render(names=fnames, header=header)
+
+    with open(os.path.join(directory, 'index.html'), 'w') as index_file:
+        index_file.write(index_content)
+
+#    subdirectories = [subdir for subdir in fnames if os.path.isdir(os.path.join(directory, subdir))]
+#    for subdir in subdirectories:
+#        generate_index(os.path.join(directory, subdir))
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("directory")
+    args = parser.parse_args()
+    generate_index(args.directory)
+
+
+if __name__ == '__main__':
+    main()

scripts/md_to_html.py

@@ -0,0 +1,57 @@
+import markdown
+import bleach
+import sys
+
+if len(sys.argv) != 3:
+    print("usage: python script.py <input markdown file> <output html file>")
+    sys.exit(1)
+
+input_markdown_file = sys.argv[1]
+output_html_file = sys.argv[2]
+
+with open(input_markdown_file, 'r') as f:
+    text = f.read()
+
+# converts the markdown to html
+html = markdown.markdown(text)
+
+# makes links that begin with https:// clickable
+html_with_links = bleach.linkify(html)
+
+# defines a template that should be at the beginning of the html
+start_template = '''<!DOCTYPE html>
+<html lang="en">
+
+<!-- this file is automatically updated when README.md is updated, please don't modify it -->
+
+<head>
+    <title>readme</title>
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <link rel="icon" type="image/png" href="/favicon.png">
+    <style>
+        body {
+            background-color: black;
+            color: white;
+            font-size: 20px;
+            font-family: sans-serif;
+        }
+
+        a {
+            color: white;
+        }
+    </style>
+</head>
+<body>
+'''
+
+# defines a template that should be at the end
+end_template = '''
+</body>
+</html>
+'''
+
+# combines them
+final_html = start_template + html_with_links + end_template
+
+with open(output_html_file, 'w') as f:
+    f.write(final_html)