initial

.gitignore

@@ -0,0 +1,3 @@
+build/
+dist/
+*.egg-info/

README.md

@@ -0,0 +1,17 @@
+# slideslurp
+
+Give slideslurp a URL to a [SlideShare](https://www.slideshare.net/)
+presentation and it will give you a PDF called `out.pdf`.
+
+I will clean this up, I promise.
+
+## Installation
+
+```
+git clone https://github.com/hellerve/slideslurp
+cd slideslurp
+python setup.py install
+```
+
+<hr/>
+Happy slurping!

requirements.txt

@@ -0,0 +1,3 @@
+requests
+bs4
+reportlab

setup.py

@@ -0,0 +1,28 @@
+# coding=utf-8
+import os
+
+from setuptools import find_packages
+from setuptools import setup
+
+setup(
+    name = 'siteslurp',
+    version = '0.0.1',
+    description = 'SlideShare to PDF',
+    author = 'Veit Heller',
+    author_email = 'veit@veitheller.de',
+    license = 'MIT License',
+    url = 'https://github.com/hellerve/slideslurp',
+    download_url = 'https://github.com/hellerve/slideslurp/tarball/0.0.1',
+    packages = find_packages('.'),
+    install_requires=[
+        "bs4",
+        "reportlab",
+        "requests",
+    ],
+    entry_points={
+        'console_scripts': [
+            'slideslurp = slideslurp:main',
+        ]
+    },
+    include_package_data = True,
+)

slideslurp/__init__.py

@@ -0,0 +1,27 @@
+import sys
+
+import bs4
+import requests
+
+from reportlab.pdfgen import canvas
+
+
+def main():
+    url = sys.argv[1]
+
+    res = requests.get(url)
+
+    tree = bs4.BeautifulSoup(res.text, "html.parser")
+    c = canvas.Canvas('out.pdf')
+
+    for img in tree.findAll("img", class_="slide_image"):
+        img_url = img.attrs["data-full"]
+        page_width, page_height = c._pagesize
+        c.setPageRotation(90)
+        c.drawImage(img_url, 0, 0, page_height, page_width, preserveAspectRatio=True)
+        c.showPage()
+    c.save()
+
+
+if __name__ == '__main__':
+    main()