Last active
March 25, 2019 19:34
-
-
Save makkoncept/45303a19fc8e8ee45d7f96555e7e9e76 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import html2text | |
from bs4 import BeautifulSoup | |
import os | |
from shutil import copy | |
path = os.path.join(os.getcwd(), "_posts") | |
_posts_files_list = os.listdir(path) | |
html_list = [file for file in _posts_files_list if ".html" in file] | |
for html_file in html_list: | |
html_file_path = os.path.join("_posts", html_file) | |
dir_path = os.path.join("tech-blog-archives", html_file[11 : len(html_file) - 5]) | |
os.makedirs(dir_path, exist_ok=True) | |
with open(html_file_path, "r") as f: | |
x = f.read() | |
h = html2text.HTML2Text() | |
h.body_width = 0 | |
y = x.split("---") | |
html = y[2] | |
metadata = y[1] | |
if "techblog.creativecommons.org" in html: | |
# change the href manually, as there is no definite pattern | |
print(html_file_path) | |
# soup = BeautifulSoup(html, "html.parser") | |
# links_list = soup.find_all("a") | |
# for link in links_list: | |
# if "techblog.creativecommons.org" in link.get("href"): | |
# old_href = link.get("href") | |
# link["href"] = "https://creativecommons.github.io/tech-blog-archives" | |
# print(link) | |
# html = str(soup) | |
# print("found the link") | |
# print(html_file_path) | |
# break | |
if "<img" in html: | |
# print(html_file_path) | |
soup = BeautifulSoup(html, "html.parser") | |
img_list = soup.find_all("img") | |
for img in img_list: | |
src = img.get("src").split("/")[1] | |
img["src"] = src | |
html = str(soup) | |
img_path = os.path.join("img", src) | |
if os.path.isfile(img_path): | |
copy(img_path, dir_path) | |
# yes_number += 1 | |
# else: | |
# no_number += 1 | |
metadata_list = metadata.split("\n") | |
meta_info = {} | |
for info in metadata_list: | |
if "title:" in info: | |
title_list = info.split(" ") | |
title = " ".join(title_list[1:]) | |
if title[0] == "'" and title[-1] == "'": | |
title = title[1 : len(title) - 1] | |
meta_info["title"] = title | |
elif "date:" in info: | |
info_list = info.split(" ") | |
meta_info["pub_date"] = info_list[1] | |
elif "display_name:" in info: | |
display_name_list = info.strip().split(" ") | |
author = display_name_list[1] | |
meta_info["author"] = author | |
elif "categories:" in info: | |
try: | |
idx = metadata_list.index("categories:") | |
categories_list = [] | |
for i in range(idx + 1, len(metadata_list)): | |
if "tags:" in metadata_list[i]: | |
break | |
categories_list.append(metadata_list[i].split(" ")[1]) | |
categories_string = ", ".join(categories_list) | |
meta_info["categories"] = categories_string | |
except ValueError: | |
meta_info["categories"] = "" | |
body = h.handle(html) | |
meta_info["body"] = body | |
content_string = f"""title: {meta_info.get('title')} | |
--- | |
categories: {meta_info.get('categories')} | |
--- | |
author: {meta_info.get('author')} | |
--- | |
body: | |
{meta_info.get('body')} | |
--- | |
pub_date: {meta_info.get('pub_date')} | |
""" | |
path_of_file = os.path.join(dir_path, "contents.lr") | |
with open(os.path.join(dir_path, "contents.lr"), "w") as f: | |
f.write(content_string) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment