pygaR: Example for pygar_form() Function

Load Libraries

library(pygaR)
library(ggplot2)
library(stringr)
library(XML)

Setup Default ggplot2 Theme

d <- theme_bw()
d <- d + theme(
    axis.text.x = element_text(angle=90, size=15),
    axis.title = element_text(size=20),
    plot.title = element_text(size=30)
)
def_theme <- d

https://www.bloomberg.com/news/articles/2017-04-28/alphabet-loves-google-ceo-so-much-he-gets-hundreds-of-millions

https://www.wsj.com/articles/google-ceo-tops-other-alphabet-execs-with-200-million-pay-1493424255

Mentions the day “Friday”, translating to 2017-04-28

Data Analysis

Search for Filings That Day

filings <- pygar_master(date=20170428, company='/alphabet inc/i')
filings

##       CIK  Company.Name Form.Type Date.Filed
## 1 1652044 Alphabet Inc.   DEF 14A   20170428
## 2 1652044 Alphabet Inc.   DEFA14A   20170428
##                                     File.Name Quarter     Date
## 1 edgar/data/1652044/0001308179-17-000170.txt       2 20170428
## 2 edgar/data/1652044/0001308179-17-000171.txt       2 20170428

Grab Form Information

form <- pygar_form(filings$File.Name[1])

Show Some Basic Form Information

names(form)

## [1] "Headers" "Body"

names(form$Header)

##  [1] "Acceptance.Datetime"        "Date.As.Of.Change"         
##  [3] "Conformed.Submission.Type"  "Filer"                     
##  [5] "Filed.As.Of.Date"           "Sec.Document"              
##  [7] "Accession.Number"           "Public.Document.Count"     
##  [9] "Effectiveness.Date"         "Conformed.Period.Of.Report"
## [11] "Sec.Header"

names(form$Body[[1]])

## [1] "Filename"    "Text"        "Description" "Text.Type"   "Type"       
## [6] "Sequence"

Find a Relevant Document

grepl('pichai', form$Body, ignore.case=TRUE) &
    grepl('schmidt', form$Body, ignore.case=TRUE)

##  [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [12] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [23] FALSE FALSE FALSE FALSE FALSE

Grab Relevant Document

doc <- form$Body[[1]]

Write To File

writeLines(doc$Text, file("alphabet.html"))

alphabet.html

Display Summary Compensation Table

sct_xmlparse <- function(html, xpath){
    html_obj <- htmlParse(html)
    xpathApply(html_obj, xpath, xmlValue)
}

sct_grab <- function(data){
    #data <- gsub("\n", "", data, fixed=TRUE)
    data <- str_trim(data)
    data <- strsplit(data, "<TABLE")[[1]]
    for(table in data){
        table <- paste0(
            "<TABLE", strsplit(table, "</TABLE>")[[1]][1], "</TABLE>",
            collapse=""
        )

        if(!is.na(
            grep("Salary", table) &&
            grep("Bonus", table) &&
            grep("Principal", table)
        )){
            data <- table
            break
        }
    }

    data <- gsub("(<[A-Z]+)[ \n][^>]+\">", "\\1>", data, ignore.case=TRUE)
    data <- gsub(">[\n ]+<", "><", data)
    data <- gsub(
        "<[\\/]?(?:(?!(?:TABLE|TR|TH|TD|P|BR))[^>])+>", "", data,
        perl=TRUE, ignore.case=TRUE
    )

    data
}

doc_table <- sct_grab(doc$Text)

## Warning: closing unused connection 6 (alphabet.html)

doc_table

[1] “

Single Parse Out

sct_table_df <- function(doc_table){

}

sct_parse <- function(doc_text){
    doc_table <- sct_grab(doc_text)
    doc_df <- sct_table_df(doc_table)
}

sct_parse(doc$Text)

alphabet_data <- pygar_master(
    startqtr=201001, endqtr=201604,
    cik=1652044, form="DEF 14A"
)

alphabet_data

##       CIK  Company.Name Form.Type Date.Filed
## 1 1652044 Alphabet Inc.   DEF 14A 2016-04-29
##                                      Filename Quarter
## 1 edgar/data/1652044/0001308179-16-000384.txt  201602

Get Google CIK

google_one <- pygar_master(qtr=201001, company='/google inc/i', form="DEF 14A")
google_cik <- google_one$CIK[1]
google_cik

## [1] 1288776

Grab More Google Data

google_data <- pygar_master(
    startqtr=200201, endqtr=201504,
    cik=google_cik, form="DEF 14A"
)

google_data

##        CIK Company.Name Form.Type Date.Filed
## 1  1288776  Google Inc.   DEF 14A 2005-04-08
## 2  1288776  Google Inc.   DEF 14A 2006-03-31
## 3  1288776  Google Inc.   DEF 14A 2007-04-04
## 4  1288776  Google Inc.   DEF 14A 2008-03-25
## 5  1288776  Google Inc.   DEF 14A 2009-03-24
## 6  1288776  Google Inc.   DEF 14A 2010-03-29
## 7  1288776  Google Inc.   DEF 14A 2011-04-20
## 8  1288776  Google Inc.   DEF 14A 2012-05-09
## 9  1288776  Google Inc.   DEF 14A 2013-04-24
## 10 1288776  Google Inc.   DEF 14A 2014-03-28
## 11 1288776  Google Inc.   DEF 14A 2015-04-23
##                                       Filename Quarter
## 1  edgar/data/1288776/0001193125-05-072803.txt  200502
## 2  edgar/data/1288776/0001193125-06-070406.txt  200601
## 3  edgar/data/1288776/0001193125-07-073756.txt  200702
## 4  edgar/data/1288776/0001193125-08-064574.txt  200801
## 5  edgar/data/1288776/0001193125-09-061999.txt  200901
## 6  edgar/data/1288776/0001193125-10-070028.txt  201001
## 7  edgar/data/1288776/0001193125-11-103802.txt  201102
## 8  edgar/data/1288776/0001193125-12-222158.txt  201202
## 9  edgar/data/1288776/0001308179-13-000248.txt  201302
## 10 edgar/data/1288776/0001308179-14-000114.txt  201401
## 11 edgar/data/1288776/0001308179-15-000157.txt  201502

Grab Google Forms

google_docs <- NULL
for(file in google_data$Filename){
    google_docs <- c(google_docs,
        pygar_form(file)$Body[[1]]$Text
    )
}

sct_grab(google_docs[10])

[1] “

Still figuring out a good way to gather this info for a graph…