mirror of
https://gitlab.com/linuxstuff/dotfiles.git
synced 2026-11-10 23:15:11 +01:00
53 lines
1002 B
Python
53 lines
1002 B
Python
import requests
|
|
import urllib.request
|
|
import time
|
|
from bs4 import BeautifulSoup
|
|
|
|
#url = 'https://www.myspass.de/shows/tvshows/stromberg/#bob-subnavi'
|
|
#response = requests.get(url)
|
|
#soup = BeautifulSoup(response.text, "html.parser")
|
|
|
|
soup = BeautifulSoup(open("./site.html"), "html.parser")
|
|
|
|
divcontents = soup.find(id="content")
|
|
divseasons = divcontents.find(id="videoPanel_overlay_10999_full_episode")
|
|
divepisodes = divseasons.findAll("div")
|
|
|
|
href = ""
|
|
prevhref = ""
|
|
title = ""
|
|
info = ""
|
|
block = 0
|
|
|
|
f = open("list.txt", "a")
|
|
|
|
for div in divepisodes:
|
|
title = ""
|
|
info = ""
|
|
|
|
atags = div.findAll("a")
|
|
for a in atags:
|
|
href = a.get('href')
|
|
|
|
h2tags = div.findAll("h2")
|
|
for h2 in h2tags:
|
|
title = h2.text
|
|
|
|
smalltags = div.findAll("small")
|
|
for small in smalltags:
|
|
info = small.text
|
|
|
|
|
|
if href != prevhref and title and info and href:
|
|
prevhref = href
|
|
#f.write("#")
|
|
#f.write('\n')
|
|
#f.write(title)
|
|
#f.write('\n')
|
|
#f.write(info)
|
|
#f.write('\n')
|
|
f.write(href)
|
|
f.write('\n')
|
|
|
|
|
|
f.close() |