Created
April 21, 2024 16:32
-
-
Save libbymiller/03c602b28d2b442df6993259de66283f to your computer and use it in GitHub Desktop.
Bodgy beautifulsoup to create an index page for a tumblr site
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
from pathlib import Path | |
import re | |
from bs4 import BeautifulSoup | |
strs = [] | |
path = "html" | |
mydir = Path(path) | |
soup_arr = [] | |
soup2 = BeautifulSoup(""" | |
<!DOCTYPE HTML> | |
<html> | |
<head> | |
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/> | |
<link rel="stylesheet" type="text/css" href="style.css"/> | |
</head> | |
<body> | |
""") | |
for file in sorted(mydir.glob('*.html')): | |
#print(file.name) | |
fn = path+"/"+file.name | |
with open(fn, 'r') as f: | |
soup = BeautifulSoup(f) | |
# add it all in | |
new_group = soup2.new_tag("div id=\""+file.name+"\"") | |
new_body = soup.find('body') | |
new_body.insert_after(new_group) | |
caption_div = soup.body.div | |
caption = None | |
if(caption_div): | |
if(caption_div.attrs.get("class")): | |
if("caption" in caption_div.attrs.get("class")): | |
caption = caption_div | |
if(caption == None): | |
caption=soup2.new_tag("div") | |
ts = soup.find_all('span') | |
tts = None | |
if(ts): | |
tts = ts[0] | |
else: | |
tts = soup2.new_tag("span") | |
embed = soup.body.embed | |
vid = None | |
if(embed): | |
src = embed['src'] | |
src2 = re.sub(r"../../", "", src) | |
src2 = re.sub(r"mp4", ".mp4", src2) | |
vid = soup2.new_tag("video",src=src2,autoplay='false',controls='true') | |
else: | |
vid = soup2.new_tag("span") | |
imgs = soup.find_all('img') | |
# add in order | |
soup2.append(caption) | |
soup2.append(tts) | |
soup2.append(vid) | |
if(imgs): | |
for img in imgs: | |
src = img['src'] | |
src2 = re.sub(r"../../", "", src) | |
i = soup2.new_tag("img",src=src2) | |
soup2.append(i) | |
# we don't need figures any more | |
for tag in soup2.find_all('figure'): | |
tag.decompose() | |
print(soup2.prettify()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment