######################################################################

library(pdftools)

download.file("http://arxiv.org/pdf/1403.2805.pdf", "1403.2805.pdf", mode = "wb")
txt <- pdf_text("1403.2805.pdf")

# first page text
cat(txt[3])

# Table of contents
toc <- pdf_toc("1403.2805.pdf")

txt <- pdf_text("http://arxiv.org/pdf/1406.4806.pdf")

# some tables
cat(txt[18])
cat(txt[19])


### read in data & clean
txt2 = pdf_text("https://goo.gl/wUXvjk")

head(txt2)

pat = "([0-9]{4} [M\\.|Mme|Mlle]{1}.*?, [n|ne]{1}.*?)\\."
data = unlist(gsubfn::strapply(txt2, pattern = pat))

head(data)