54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
import urllib.parse
|
|
from weasyprint import HTML
|
|
|
|
class MLWerk:
|
|
class SubSite:
|
|
def __init__(self, url):
|
|
self.url = url
|
|
self.getsoup()
|
|
|
|
def getsoup(self):
|
|
r = requests.get(self.url)
|
|
r.encoding = 'UTF-8'
|
|
self.soup = BeautifulSoup(r.text, 'html.parser')
|
|
|
|
def __init__(self, url):
|
|
self.url = url
|
|
self.baseurl = url[:url.rfind('/')] + '/'
|
|
self.subsites = []
|
|
self.getsoup()
|
|
|
|
def getsoup(self):
|
|
r = requests.get(self.url)
|
|
r.encoding = 'UTF-8'
|
|
self.soup = BeautifulSoup(r.text, 'html.parser')
|
|
|
|
def getsubsites(self, limit = None):
|
|
i = 0
|
|
for link in self.soup.find_all('a'):
|
|
if limit != None and i > limit:
|
|
break
|
|
link = link.get('href')
|
|
if not link == None and not ("#" in link or "/" in link):
|
|
self.subsites.append(self.SubSite(urllib.parse.urljoin(self.baseurl, link)))
|
|
i += 1
|
|
|
|
def concatsubsites(self):
|
|
for subsite in self.subsites:
|
|
for tag in subsite.soup.body:
|
|
if (tag != "\n" and tag.name != "a"):
|
|
self.soup.body.append(tag)
|
|
|
|
def genpdf(self, path):
|
|
HTML(string=str(self.soup)).write_pdf(path)
|
|
|
|
def text2pdf(self, path, dry=False):
|
|
print("gettings subsites")
|
|
self.getsubsites()
|
|
print("concatting subsites")
|
|
self.concatsubsites()
|
|
if not dry:
|
|
print("generating pdf")
|
|
self.genpdf(path) |