\documentclass[10pt,a4paper]{article}

% Packages
\usepackage{fancyhdr}           % For header and footer
\usepackage{multicol}           % Allows multicols in tables
\usepackage{tabularx}           % Intelligent column widths
\usepackage{tabulary}           % Used in header and footer
\usepackage{hhline}             % Border under tables
\usepackage{graphicx}           % For images
\usepackage{xcolor}             % For hex colours
%\usepackage[utf8x]{inputenc}    % For unicode character support
\usepackage[T1]{fontenc}        % Without this we get weird character replacements
\usepackage{colortbl}           % For coloured tables
\usepackage{setspace}           % For line height
\usepackage{lastpage}           % Needed for total page number
\usepackage{seqsplit}           % Splits long words.
%\usepackage{opensans}          % Can't make this work so far. Shame. Would be lovely.
\usepackage[normalem]{ulem}     % For underlining links
% Most of the following are not required for the majority
% of cheat sheets but are needed for some symbol support.
\usepackage{amsmath}            % Symbols
\usepackage{MnSymbol}           % Symbols
\usepackage{wasysym}            % Symbols
%\usepackage[english,german,french,spanish,italian]{babel}              % Languages

% Document Info
\author{gonz95alo}
\pdfinfo{
  /Title (network-data-mining.pdf)
  /Creator (Cheatography)
  /Author (gonz95alo)
  /Subject (Network data mining Cheat Sheet)
}

% Lengths and widths
\addtolength{\textwidth}{6cm}
\addtolength{\textheight}{-1cm}
\addtolength{\hoffset}{-3cm}
\addtolength{\voffset}{-2cm}
\setlength{\tabcolsep}{0.2cm} % Space between columns
\setlength{\headsep}{-12pt} % Reduce space between header and content
\setlength{\headheight}{85pt} % If less, LaTeX automatically increases it
\renewcommand{\footrulewidth}{0pt} % Remove footer line
\renewcommand{\headrulewidth}{0pt} % Remove header line
\renewcommand{\seqinsert}{\ifmmode\allowbreak\else\-\fi} % Hyphens in seqsplit
% This two commands together give roughly
% the right line height in the tables
\renewcommand{\arraystretch}{1.3}
\onehalfspacing

% Commands
\newcommand{\SetRowColor}[1]{\noalign{\gdef\RowColorName{#1}}\rowcolor{\RowColorName}} % Shortcut for row colour
\newcommand{\mymulticolumn}[3]{\multicolumn{#1}{>{\columncolor{\RowColorName}}#2}{#3}} % For coloured multi-cols
\newcolumntype{x}[1]{>{\raggedright}p{#1}} % New column types for ragged-right paragraph columns
\newcommand{\tn}{\tabularnewline} % Required as custom column type in use

% Font and Colours
\definecolor{HeadBackground}{HTML}{333333}
\definecolor{FootBackground}{HTML}{666666}
\definecolor{TextColor}{HTML}{333333}
\definecolor{DarkBackground}{HTML}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\renewcommand{\familydefault}{\sfdefault}
\color{TextColor}

% Header and Footer
\pagestyle{fancy}
\fancyhead{} % Set header to blank
\fancyfoot{} % Set footer to blank
\fancyhead[L]{
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{C}
    \SetRowColor{DarkBackground}
    \vspace{-7pt}
    {\parbox{\dimexpr\textwidth-2\fboxsep\relax}{\noindent
        \hspace*{-6pt}\includegraphics[width=5.8cm]{/web/www.cheatography.com/public/images/cheatography_logo.pdf}}
    }
\end{tabulary}
\columnbreak
\begin{tabulary}{11cm}{L}
    \vspace{-2pt}\large{\bf{\textcolor{DarkBackground}{\textrm{Network data mining Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{gonz95alo} via \textcolor{DarkBackground}{\uline{cheatography.com/152363/cs/32833/}}}
\end{tabulary}
\end{multicols}}

\fancyfoot[L]{ \footnotesize
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{LL}
  \SetRowColor{FootBackground}
  \mymulticolumn{2}{p{5.377cm}}{\bf\textcolor{white}{Cheatographer}}  \\
  \vspace{-2pt}gonz95alo \\
  \uline{cheatography.com/gonz95alo} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Not Yet Published.\\
   Updated 27th June, 2022.\\
   Page {\thepage} of \pageref{LastPage}.
\end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Sponsor}}  \\
  \SetRowColor{white}
  \vspace{-5pt}
  %\includegraphics[width=48px,height=48px]{dave.jpeg}
  Measure your website readability!\\
  www.readability-score.com
\end{tabulary}
\end{multicols}}




\begin{document}
\raggedright
\raggedcolumns

% Set font size to small. Switch to any value
% from this page to resize cheat sheet text:
% www.emerson.emory.edu/services/latex/latex_169.html
\footnotesize % Small font.

\begin{multicols*}{2}

\begin{tabularx}{8.4cm}{x{3.36 cm} x{4.64 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Web scraping with urllib}}  \tn
% Row 0
\SetRowColor{LightBackground}
Import basic functions & `from urllib.request import urlopen, urlretrieve, Request` \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
Request webpage 'example.com' & `raw\_request = \seqsplit{Request('https://example}.com')` \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Add headers (I) & \seqsplit{`raw\_request.add\_header('User-Agent'}, 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:78.0) Gecko/20100101 Firefox/78.0')` \tn 
% Row Count 11 (+ 6)
% Row 3
\SetRowColor{white}
Add headers (II) & \seqsplit{`raw\_request.add\_header('Accept'}, 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,{\emph{/}};q=0.8')` \tn 
% Row Count 16 (+ 5)
% Row 4
\SetRowColor{LightBackground}
Get HTML code as a string & `html = \seqsplit{urlopen(raw\_request).read().decode("utf-8")`} \tn 
% Row Count 19 (+ 3)
% Row 5
\SetRowColor{white}
Download file & `urlretrieve(fileURL, \seqsplit{'file\_name\_in\_destination')`} \tn 
% Row Count 22 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4.32 cm} x{3.68 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Python libraries}}  \tn
% Row 0
\SetRowColor{LightBackground}
urllib: URL handling & `import urllib` \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
BeautifulSoup: HTML/XML parser & `from bs4 import BeautifulSoup` \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Regular expressions: pattern matching & `import re` \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
NetworkX: network analysis & `import networkx as nx` \tn 
% Row Count 7 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4.16 cm} x{3.84 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Websites of interest}}  \tn
% Row 0
\SetRowColor{LightBackground}
Stanford Network Analysis Project & \seqsplit{http://snap.stanford.edu/} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Koblenz Network Collection & http://konect.cc/ \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Network Repository & \seqsplit{https://networkrepository}.com/ \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{1.672 cm} x{3.42 cm} x{2.508 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{Graph dataset formats}}  \tn
% Row 0
\SetRowColor{LightBackground}
GML (.gml) & {\emph{Custom structure}} & `G = \seqsplit{nx.read\_gml(path)`} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Pajek (.net) & {\emph{Custom structure}} & `G = \seqsplit{nx.read\_pajek(path)`} \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
JSON (.json) & {\emph{Custom structure}} & `G = \seqsplit{nx.read\_json(path)`} \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
Plain text & `node1 node2 weight` & Manual \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{Multilayer} v1 (.) & `layer node1 node2 weight` & Manual \tn 
% Row Count 11 (+ 3)
% Row 5
\SetRowColor{white}
\seqsplit{Multilayer} v2 (.) & `layer1 layer2 node1 node2 weight` & Manual \tn 
% Row Count 14 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{8.4cm}}{Those formats without a specific function are usually easy to parse manually.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{p{0.8 cm} p{0.8 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Beautiful Soup HTML parsing}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{} \tn 
% Row Count 0 (+ 0)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.04 cm} x{4.96 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{String slicing tricks}}  \tn
% Row 0
\SetRowColor{LightBackground}
Split by character & `'a\_string'.split('\_')` \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Join with a character & `'\_'.join({[}'a', 'string'{]})` \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Capitalize & `foo.capitalize()` \tn 
% Row Count 5 (+ 1)
% Row 3
\SetRowColor{white}
Capitalize, lower, upper & `foo.capitalize(), foo.lower(), foo.upper()` \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
Find, count & `foo.find('e'), foo.count('e')` \tn 
% Row Count 9 (+ 2)
% Row 5
\SetRowColor{white}
Replace & \seqsplit{`'a\_string.replace('string'}, 'banana')'` \tn 
% Row Count 11 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{p{0.8 cm} p{0.8 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Regular Expressions}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{} \tn 
% Row Count 0 (+ 0)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


% That's all folks
\end{multicols*}

\end{document}