(no subject)

[pangolin20]

Below the cut, there is a Python program which builds an index of the front page or day view of a Dreamwidth blog. I've used it to great success to keep an index of one of the communities I'm part of.

import requests

def getLinks(slug):

url1= f'htt‌ps://[journal/community name goes here].dreamwidth.org{slug}'

content = requests.get(url1).content

content_split = str(content).split("\\n")

url_title = ""

url_cut = ""

for i in range(len(content_split)):

if 'a title' in content_split[i]:

f = content_split[i]

title_line = f.split("\">")

if 'lj:user' and 'Sticky' not in title_line[0]:

f_2 = title_line[1].split("=\"")

real_href = f_2[2]

title = f_2[1].split("\" h")

url_title += "<a href=\"" + real_href + "\">" + title[0]

if 'cutid' in content_split[i]:

g = content_split[i].split("cutid")

for z in range(len(g)):

if z > 0:

h = g[z].split("</a>")

index = h[0].split(">")

if 'Read more...' != index[1]:

url_cut += " [" + index[1] + "]"

if 'Read more...' == index[1]:

url_cut = ""

if 'footer' in content_split[i]:

if len(url_title) > 0:

print(url_title + url_cut + "</a>")

url_cut = ""

url_title = ""

getLinks('/')