15 |
16 | [](http://www.abj.org.br) [](https://travis-ci.org/courtsbr/esaj) [](https://ci.appveyor.com/project/courtsbr/esaj)
17 |
18 | ## Overview
19 |
20 | The `esaj` R package is a simple interface that allows you to download multiple
21 | kinds of files from Brazil's e-SAJ (Electronic Justice Automation System)
22 | portals. With this package you can save and parse lawsuits, queries, and
23 | decisions with very simple, tidyverse compliant functions.
24 |
25 | To install `esaj`, run the code below:
26 |
27 | ```{r, eval = FALSE}
28 | # install.packages("devtools")
29 | devtools::install_github("courtsbr/esaj")
30 | ```
31 |
32 | ## Usage
33 |
34 | ### Lawsuits
35 |
36 | Before `esaj` if you wanted to gather information about lawsuits being
37 | processed by Brazil's state-level Judiciary, you would have to go to each
38 | state's e-SAJ portal, manually input each lawsuit's ID, break a capthca, and
39 | only then download an HTML with the information you wanted; now you can simply
40 | run `download_cpopg()` or `download_cposg()`, and spend your valuable time
41 | analysing the data.
42 |
43 | ```{r, message = FALSE}
44 | # Download first degree lawsuits from multiple states
45 | ids <- c(
46 | "0123479-07.2012.8.26.0100",
47 | "0552486-62.2015.8.05.0001",
48 | "0303349-44.2014.8.24.0020")
49 | esaj::download_cpopg(ids, "~/Desktop/")
50 |
51 | # Download second degree lawsuits from São Paulo
52 | ids <- c(
53 | "1001869-51.2017.8.26.0562",
54 | "1001214-07.2016.8.26.0565")
55 | esaj::download_cposg(ids, "~/Desktop/")
56 | ```
57 |
58 | For more information on how to use these functions and which TJs are
59 | implemented, please see [Downloading Lawsuits](http://courtsbr.github.io/esaj/articles/download_lawsuit.html).
60 |
61 | ### Queries
62 |
63 | Besides downloading lawsuits (see the **Downloading Lawsuits** article), `esaj`
64 | also allows the user to download the results of a query on lawsuits. This kind
65 | of query is very useful for finding out what lawsuits contain certain words,
66 | were filed in a given period, were filed in a given court, etc.
67 |
68 |
69 | ```{r}
70 | # Download results of a simple first degree query
71 | esaj::download_cjpg("recurso", "~/Desktop/")
72 |
73 | # Download results of a slightly more complex second degree query
74 | esaj::download_cjsg("recurso", "~/Desktop/", classes = c("1231", "1232"))
75 | ```
76 |
77 | For more information on how to use these functions and all their auxiliary
78 | methods (like `peek_cj*g()` and `cj*g_table()`), please see
79 | [Downloading Queries](http://courtsbr.github.io/esaj/articles/download_query.html).
80 |
81 | ### Decisions
82 |
83 | Of all functions in the `esaj` package, `download_decision()` is probably the
84 | simplest: it downloads the PDF belonging to a decision and that's it.
85 |
86 |
87 | ```{r}
88 | # Download one decision
89 | esaj::download_decision("10000034", "~/Desktop/")
90 |
91 | # Download more than one decision
92 | esaj::download_decision(c("10800758", "10000034"), "~/Desktop/")
93 | ```
94 |
95 | For more information on how to use this function, please see
96 | [Downloading Decisions](http://courtsbr.github.io/esaj/articles/download_decision.html).
97 |
--------------------------------------------------------------------------------
/R/parse_cjpg.R:
--------------------------------------------------------------------------------
1 |
2 | #' Parse one lawsuit from a CJSG page
3 | #'
4 | #' @param node A `.fundocinza1` node extracted from the page
5 | #' @return One row with the data concerning the lawsuit
6 | parse_cjpg_lawsuit <- function(node) {
7 |
8 | # Get complicated variables
9 | cd <- node %>%
10 | xml2::xml_find_first(".//a[@title='Visualizar Inteiro Teor']") %>%
11 | rvest::html_attr("name") %>%
12 | stringr::str_trim()
13 | id <- node %>%
14 | xml2::xml_find_first(".//a[@title='Visualizar Inteiro Teor']") %>%
15 | rvest::html_text() %>%
16 | stringr::str_trim() %>%
17 | stringr::str_replace_all("[^0-9]", "")
18 | tx <- node %>%
19 | rvest::html_node(xpath = ".//table//div[@style='display: none;']") %>%
20 | rvest::html_text() %>%
21 | stringr::str_trim()
22 |
23 | # Create table prototype
24 | keys <- node %>%
25 | rvest::html_nodes("table > tr > td > strong") %>%
26 | rvest::html_text() %>%
27 | stringr::str_trim() %>%
28 | stringr::str_to_lower() %>%
29 | rm_accent() %>%
30 | stringr::str_trim() %>%
31 | stringr::str_replace_all("[^0-9a-z]+", "_") %>%
32 | stringr::str_replace_all("^_|_$", "")
33 | vals <- node %>%
34 | xml2::xml_find_all(".//table/tr/td/strong/following-sibling::text()[1]") %>%
35 | rvest::html_text() %>%
36 | stringr::str_trim()
37 | infos <- tibble::tibble(key = keys, val = vals) %>%
38 | dplyr::mutate(id = 1) %>%
39 | tidyr::spread(key, val) %>%
40 | dplyr::select(-id)
41 |
42 | # Build final table
43 | tibble::tibble(id_lawsuit = id, code_lawsuit = cd) %>%
44 | dplyr::bind_cols(infos) %>%
45 | dplyr::mutate(summary = tx)
46 | }
47 |
48 | #' Parse a page of CJPG results
49 | #'
50 | #' @param file The path to the file to be parsed
51 | #' @param pb Progress bar created by [parse_cjpg()]
52 | #' @return A tibble with the parsed information
53 | parse_cjpg_ <- function(file, pb = NULL) {
54 |
55 | # Safely parse everything
56 | parse <- purrr::possibly(parse_cjpg_lawsuit, tibble::tibble(), quiet = FALSE)
57 |
58 | # Iterate over xml nodes to parse every lawsuit
59 | table <- file %>%
60 | xml2::read_html("UTF-8") %>%
61 | rvest::html_nodes(".fundocinza1") %>%
62 | purrr::map_dfr(parse)
63 |
64 | if (!is.null(pb)) { pb$tick() }
65 | return(table)
66 | }
67 |
68 | #' Parse lawsuits extracted from CJPG query
69 | #'
70 | #' @param file Character vector with the paths to one or more files
71 | #' @param cores Number of cores to use when parsing
72 | #'
73 | #' @return A tibble with the columns
74 | #' \itemize{
75 | #' \item `file` Name of the file
76 | #' \item `id_lawsuit` Number of the lawsuit (doesn't have to be unique)
77 | #' \item `code_lawsuit` Unique code of the lawsuit
78 | #' \item `subject` Subject of the lawsuit
79 | #' \item `class` Class of the subject
80 | #' \item `district` Name of the district
81 | #' \item `date_available` Date when lawsuit was made available (\%d/\%m/\%Y)
82 | #' \item `jurisdiction` Name of the jurisdiction
83 | #' \item `judge` Name of the judge
84 | #' \item `court` Body responsible for the lawsuit
85 | #' \item `summary` Summary of the ruling
86 | #' }
87 | #' @export
88 | parse_cjpg <- function(file, cores = 1) {
89 |
90 | # Set names for .id
91 | names(file) <- file
92 | file <- file[file.size(file) > 0]
93 |
94 | # Run either with progress bar or on parallel
95 | if (cores == 1) {
96 | pb <- progress::progress_bar$new(total = length(file))
97 | purrr::map_dfr(file, parse_cjpg_, pb, .id = "file")
98 | } else {
99 | file %>%
100 | parallel::mclapply(parse_cjpg_, mc.cores = cores) %>%
101 | dplyr::bind_rows(.id = "file")
102 | }
103 | }
104 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 |
2 | esaj
3 | =====================================================
4 |
5 | [](http://www.abj.org.br) [](https://travis-ci.org/courtsbr/esaj) [](https://ci.appveyor.com/project/courtsbr/esaj)
6 |
7 | Overview
8 | --------
9 |
10 | The `esaj` R package is a simple interface that allows you to download multiple kinds of files from Brazil's e-SAJ (Electronic Justice Automation System) portals. With this package you can save and parse lawsuits, queries, and decisions with very simple, tidyverse compliant functions.
11 |
12 | To install `esaj`, run the code below:
13 |
14 | ``` r
15 | # install.packages("devtools")
16 | devtools::install_github("courtsbr/esaj")
17 | ```
18 |
19 | Usage
20 | -----
21 |
22 | ### Lawsuits
23 |
24 | Before `esaj` if you wanted to gather information about lawsuits being processed by Brazil's state-level Judiciary, you would have to go to each state's e-SAJ portal, manually input each lawsuit's ID, break a capthca, and only then download an HTML with the information you wanted; now you can simply run `download_cpopg()` or `download_cposg()`, and spend your valuable time analysing the data.
25 |
26 | ``` r
27 | # Download first degree lawsuits from multiple states
28 | ids <- c(
29 | "0123479-07.2012.8.26.0100",
30 | "0552486-62.2015.8.05.0001",
31 | "0303349-44.2014.8.24.0020")
32 | esaj::download_cpopg(ids, "~/Desktop/")
33 | #> [1] "/Users/user/Desktop/01234790720128260100.html"
34 | #> [2] "/Users/user/Desktop/05524866220158050001.html"
35 | #> [3] "/Users/user/Desktop/03033494420148240020.html"
36 |
37 | # Download second degree lawsuits from São Paulo
38 | ids <- c(
39 | "1001869-51.2017.8.26.0562",
40 | "1001214-07.2016.8.26.0565")
41 | esaj::download_cposg(ids, "~/Desktop/")
42 | #> [1] "/Users/user/Desktop/10018695120178260562.html"
43 | #> [2] "/Users/user/Desktop/10012140720168260565.html"
44 | ```
45 |
46 | For more information on how to use these functions and which TJs are implemented, please see [Downloading Lawsuits](http://courtsbr.github.io/esaj/articles/download_lawsuit.html).
47 |
48 | ### Queries
49 |
50 | Besides downloading lawsuits (see the **Downloading Lawsuits** article), `esaj` also allows the user to download the results of a query on lawsuits. This kind of query is very useful for finding out what lawsuits contain certain words, were filed in a given period, were filed in a given court, etc.
51 |
52 | ``` r
53 | # Download results of a simple first degree query
54 | esaj::download_cjpg("recurso", "~/Desktop/")
55 | #> [1] "/Users/user/Desktop/search.html"
56 | #> [2] "/Users/user/Desktop/page1.html"
57 |
58 | # Download results of a slightly more complex second degree query
59 | esaj::download_cjsg("recurso", "~/Desktop/", classes = c("1231", "1232"))
60 | #> [1] "/Users/user/Desktop/search.html"
61 | #> [2] "/Users/user/Desktop/page1.html"
62 | ```
63 |
64 | For more information on how to use these functions and all their auxiliary methods (like `peek_cj*g()` and `cj*g_table()`), please see [Downloading Queries](http://courtsbr.github.io/esaj/articles/download_query.html).
65 |
66 | ### Decisions
67 |
68 | Of all functions in the `esaj` package, `download_decision()` is probably the simplest: it downloads the PDF belonging to a decision and that's it.
69 |
70 | ``` r
71 | # Download one decision
72 | esaj::download_decision("10000034", "~/Desktop/")
73 | #> [1] "/Users/user/Desktop/10000034.pdf"
74 |
75 | # Download more than one decision
76 | esaj::download_decision(c("10800758", "10000034"), "~/Desktop/")
77 | #> [1] "/Users/user/Desktop/10800758.pdf"
78 | #> [2] "/Users/user/Desktop/10000034.pdf"
79 | ```
80 |
81 | For more information on how to use this function, please see [Downloading Decisions](http://courtsbr.github.io/esaj/articles/download_decision.html).
82 |
--------------------------------------------------------------------------------
/docs/reference/make_parser.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
119 |
120 |
121 |
122 |
--------------------------------------------------------------------------------
/docs/reference/pipe.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
112 |
113 |
118 |
93 |
105 |
111 |
94 |
96 |
97 |
98 | Makes a parser
95 |Makes a parser
99 | 100 | 101 |make_parser()
102 |
103 |
104 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
119 |
120 |
121 |
122 |
--------------------------------------------------------------------------------
/docs/reference/op-definition.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
112 |
113 |
118 |
93 |
105 |
111 |
94 |
96 |
97 |
98 | Pipe operator
95 |See %>% for more details.
See %<>% for more details.
37 |
38 |
87 |
88 |
89 |
90 |
91 |
118 |
119 |
120 |
121 |
--------------------------------------------------------------------------------
/docs/articles/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
111 |
112 |
117 |
93 |
104 |
110 |
94 |
96 |
97 |
98 | Definition operator
95 |See := for more details.
37 |
38 |
87 |
88 |
89 |
90 |
91 |
116 |
117 |
118 |
119 |
--------------------------------------------------------------------------------
/docs/authors.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
94 |
95 | Articles version 0.0.0.9000
93 |
96 |
109 |
110 |
115 |
97 |
108 |
98 |
107 | All vignettes
99 | 100 | 101 |-
102 |
- Downloading Decisions 103 |
- Downloading Lawsuits 104 |
- Downloading Queries 105 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
129 |
130 |
131 |
132 |
--------------------------------------------------------------------------------
/docs/reference/parse_parts.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
122 |
123 |
128 |
93 |
105 |
111 |
112 |
113 |
114 |
121 |
94 |
96 |
97 |
98 | Parses data
95 |Parses data
99 | 100 | 101 |parse_data(parser)102 | 103 |
Arguments
104 || parser | 108 |A parser returned by |
109 |
|---|
37 |
38 |
87 |
88 |
89 |
90 |
91 |
129 |
130 |
131 |
132 |
--------------------------------------------------------------------------------
/docs/reference/parse_movs.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
122 |
123 |
128 |
93 |
105 |
111 |
112 |
113 |
114 |
121 |
94 |
96 |
97 |
98 | Parses parts
95 |Parses parts
99 | 100 | 101 |parse_parts(parser)102 | 103 |
Arguments
104 || parser | 108 |A parser returned by |
109 |
|---|
37 |
38 |
87 |
88 |
89 |
90 |
91 |
129 |
130 |
131 |
132 |
--------------------------------------------------------------------------------
/docs/reference/parse_decisions.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
122 |
123 |
128 |
93 |
105 |
111 |
112 |
113 |
114 |
121 |
94 |
96 |
97 |
98 | Parses movements
95 |Parses movements
99 | 100 | 101 |parse_movs(parser)102 | 103 |
Arguments
104 || parser | 108 |A parser returned by |
109 |
|---|
37 |
38 |
87 |
88 |
89 |
90 |
91 |
129 |
130 |
131 |
132 |
--------------------------------------------------------------------------------
/R/parse_cposg.R:
--------------------------------------------------------------------------------
1 |
2 | #' Parses parts
3 | #' @param parser A parser returned by [make_parser()]
4 | #' @export
5 | parse_parts.cposg <- function(parser) {
6 |
7 | # Check class
8 | stopifnot("parser" %in% class(parser))
9 |
10 | # Function for getting parts
11 | get_parts <- function(html) {
12 | html %>%
13 | xml2::xml_find_all("//*[@id='tablePartesPrincipais']") %>%
14 | rvest::html_table(fill = TRUE) %>%
15 | purrr::pluck(1) %>%
16 | dplyr::as_tibble() %>%
17 | dplyr::mutate(
18 | X2 = stringr::str_split(X2, " "),
19 | id = 1:nrow(.)) %>%
20 | tidyr::unnest(X2) %>%
21 | dplyr::mutate(
22 | part = str_replace_all(X1, "[^a-zA-Z]", ""),
23 | role = stringr::str_extract(dplyr::lag(X2), "\\t [a-zA-Z]+:"),
24 | role = str_replace_all(role, "[^a-zA-Z]", ""),
25 | role = ifelse(is.na(role), part, role),
26 | name = str_replace_all(X2, " ?\\n.+", "")) %>%
27 | dplyr::select(id, name, part, role)
28 | }
29 |
30 | # Add get_parts to getters
31 | purrr::list_merge(parser, name = "parts", getter = get_parts)
32 | }
33 |
34 | #' Parses data
35 | #' @param parser A parser returned by [make_parser()]
36 | #' @export
37 | parse_data.cposg <- function(parser) {
38 |
39 | # Check class
40 | stopifnot("parser" %in% class(parser))
41 |
42 | # Function for getting data
43 | get_data <- function(html) {
44 | html %>%
45 | xml2::xml_find_all("//*[@class='secaoFormBody']") %>%
46 | rvest::html_table(fill = TRUE) %>%
47 | purrr::pluck(2) %>%
48 | dplyr::as_tibble() %>%
49 | dplyr::filter(!(is.na(X2) & is.na(X3))) %>%
50 | dplyr::select(-X3) %>%
51 | dplyr::add_row(
52 | X1 = "Situa\u00E7\u00E3o",
53 | X2 = stringr::str_extract(.[1, 2], "[A-Za-z]+$")) %>%
54 | dplyr::mutate(
55 | X1 = str_replace_all(X1, ":", ""),
56 | X2 = str_replace_all(X2, " ?[\\n\\t].+", ""),
57 | X2 = str_replace_all(X2, "\\n", "")) %>%
58 | purrr::set_names("data", "value")
59 | }
60 |
61 | # Add get_data to getters
62 | purrr::list_merge(parser, name = "data", getter = get_data)
63 | }
64 |
65 | #' Parses movements
66 | #' @param parser A parser returned by [make_parser()]
67 | #' @export
68 | parse_movs.cposg <- function(parser) {
69 |
70 | # Check class
71 | stopifnot("parser" %in% class(parser))
72 |
73 | # Function for getting movements
74 | get_movs <- function(html) {
75 | xp0 <- "//*[@id='tabelaTodasMovimentacoes']"
76 | tab <- xml2::xml_find_all(html, paste0(xp0, "//parent::table"))
77 | tab %>%
78 | rvest::html_table(fill = TRUE) %>%
79 | purrr::pluck(1) %>%
80 | janitor::clean_names() %>%
81 | dplyr::as_tibble() %>%
82 | dplyr::select(movement = data, X3 = movimento) %>%
83 | dplyr::filter(movement != "") %>%
84 | tidyr::separate(X3, c("title", "txt"), sep = "\n\t",
85 | extra = "merge", fill = "right") %>%
86 | dplyr::mutate_all(stringr::str_squish) %>%
87 | dplyr::mutate(movement = lubridate::dmy(movement, quiet = TRUE))
88 | }
89 |
90 | # Add get_movs to getters
91 | purrr::list_merge(parser, name = "movs", getter = get_movs)
92 | }
93 |
94 | #' Parses decisions
95 | #' @param parser A parser returned by [make_parser()]
96 | #' @export
97 | parse_decisions.cposg <- function(parser){
98 |
99 | # Check class
100 | stopifnot("parser" %in% class(parser))
101 |
102 | # Function for getting decisions
103 | get_decisions <- function(html) {
104 |
105 | #Gets all eligible tables
106 | tables <- html %>%
107 | xml2::xml_find_all("//table[@style='margin-left:15px; margin-top:1px;']")
108 |
109 | #Beginning of the table
110 | first_table <- tables %>%
111 | rvest::html_text() %>%
112 | stringr::str_which("Situa\u00e7\u00e3o do julgamento") %>%
113 | max()
114 |
115 | #Check if first_table is Inf
116 | if(is.infinite(first_table)){return(dplyr::data_frame(date = NA, decision = NA))}
117 |
118 | #End of the table
119 | last_table <- length(tables)
120 |
121 | tables[first_table:last_table] %>%
122 | rvest::html_table(fill = TRUE) %>%
123 | dplyr::bind_rows() %>%
124 | dplyr::as_tibble() %>%
125 | dplyr::mutate(
126 | X1 = lubridate::dmy(X1, quiet = TRUE),
127 | X2 = stringr::str_replace_all(X2, "[:space:]+"," "),
128 | X3 = stringr::str_replace_all(X3, "[:space:]+", " ")) %>%
129 | dplyr::select(-X2) %>%
130 | dplyr::filter(!is.na(X1)) %>%
131 | purrr::set_names("date", "decision")
132 | }
133 |
134 | # Add get_decisions to getters
135 | purrr::list_merge(parser, name = "decisions", getter = get_decisions)
136 | }
137 |
--------------------------------------------------------------------------------
/R/parse_cjsg.R:
--------------------------------------------------------------------------------
1 | #' Parse lawsuits extracted from CJSG query
2 | #'
3 | #' @param file Character vector with the paths to one or more files
4 | #' @param cores Number of cores to use when parsing
5 | #'
6 | #' @return A tibble with the columns
7 | #' \itemize{
8 | #' \item `file` Name of the file
9 | #' \item `id_page` ID found in the page
10 | #' \item `id_decision` Unique ID of the ruling
11 | #' \item `id_lawsuit` Number of the lawsuit (doesn't have to be unique)
12 | #' \item `class_subject` Class/subject, separated by slashes
13 | #' \item `district` Name of the district
14 | #' \item `court` Body responsible for the appeal
15 | #' \item `date_decision` Date of the judgement (\%d/\%m/\%Y)
16 | #' \item `date_publication` Date of the publication (\%d/\%m/\%Y)
17 | #' \item `date_registration` Date of registration in the system (\%d/\%m/\%Y)
18 | #' \item `rapporteur` Name of the rapporteur
19 | #' \item `summary` Summary of the ruling
20 | #' \item `txt_summary` Text of the summary with no formatting
21 | #' }
22 | #' @export
23 | parse_cjsg <- function(file, cores = 1) {
24 |
25 | # Set names for .id
26 | names(file) <- file
27 | file <- file[file.size(file) > 0]
28 |
29 | # Run either with progress bar or on parallel
30 | if (cores == 1) {
31 | pb <- progress::progress_bar$new(total = length(file))
32 | purrr::map_dfr(file, parse_cjsg_, pb, .id = "file")
33 | } else {
34 | file %>%
35 | parallel::mclapply(parse_cjsg_, mc.cores = cores) %>%
36 | dplyr::bind_rows(.id = "file")
37 | }
38 | }
39 |
40 | #' Parse a page of CJSG results
41 | #'
42 | #' @param file The path to the file to be parsed
43 | #' @param pb Progress bar created by [parse_cjsg()]
44 | #' @return A tibble with the parsed information
45 | parse_cjsg_ <- function(file, pb = NULL) {
46 |
47 | # Safely parse everything
48 | parse <- purrr::possibly(parse_cjsg_lawsuit, tibble::tibble(), quiet = FALSE)
49 |
50 | # Iterate over xml nodes to parse every lawsuit
51 | table <- file %>%
52 | xml2::read_html("UTF-8") %>%
53 | rvest::html_nodes(".fundocinza1") %>%
54 | purrr::map_dfr(parse)
55 |
56 | if (!is.null(pb)) { pb$tick() }
57 | return(table)
58 | }
59 |
60 | #' Parse one lawsuit from a CJSG page
61 | #'
62 | #' @param node A `.fundocinza1` node extracted from the page
63 | #' @return One row with the data concerning the lawsuit
64 | parse_cjsg_lawsuit <- function(node) {
65 |
66 | # Auxiliary function to fill in missing columns in table
67 | fill_in_columns <- function(data) {
68 |
69 | # Fill in ementa and publicacao
70 | if (!tibble::has_name(data, "ementa"))
71 | data <- dplyr::mutate(data, ementa = NA_character_)
72 | if (!tibble::has_name(data, "data_publicacao"))
73 | data <- dplyr::mutate(data, data_publicacao = NA_character_)
74 |
75 | return(data)
76 | }
77 |
78 | # Auxiliary function to create a column that doesn't exist
79 | fncols <- function(data, cname) {
80 | add <-cname[!cname%in%names(data)]
81 |
82 | if(length(add)!=0) data[add] <- NA_character_
83 | data
84 | }
85 |
86 | # Get information from lawsuit
87 | tmp <- rvest::html_node(node, ".downloadEmenta")
88 | infos <- tibble::tibble(
89 | id_lawsuit = stringr::str_trim(rvest::html_text(tmp)),
90 | id_decision = rvest::html_attr(tmp, "cdacordao"))
91 |
92 | # Get complicated variables
93 | id <- node %>%
94 | rvest::html_node(".ementaClass") %>%
95 | rvest::html_text() %>%
96 | stringr::str_trim() %>%
97 | stringr::str_replace_all("[^0-9]", "")
98 | cs <- node %>%
99 | rvest::html_node(".assuntoClasse") %>%
100 | rvest::html_text() %>%
101 | stringr::str_trim()
102 | ts <- node %>%
103 | rvest::html_node("textarea") %>%
104 | rvest::html_text()
105 |
106 | # Create final table
107 | node %>%
108 | rvest::html_nodes(".ementaClass2") %>%
109 | rvest::html_text() %>%
110 | stringr::str_split_fixed(":", 2) %>%
111 | tibble::as_tibble() %>%
112 | purrr::set_names(c("key", "val")) %>%
113 | dplyr::mutate_all(stringr::str_trim) %>%
114 | dplyr::mutate(
115 | key = key %>%
116 | rm_accent() %>%
117 | stringr::str_to_lower() %>%
118 | stringr::str_replace_all(" +", "_") %>%
119 | stringr::str_replace_all("[^a-z_]", "") %>%
120 | stringr::str_replace_all("_d[eo]_", "_")) %>%
121 | tidyr::spread(key, val) %>%
122 | dplyr::bind_cols(infos) %>%
123 | fill_in_columns() %>%
124 | dplyr::mutate(id = id, cs = cs, ts = ts) %>%
125 | fncols("data_julgamento") %>%
126 | dplyr::select(
127 | id_page = id, id_decision, id_lawsuit, class_subject = cs,
128 | district = comarca, court = orgao_julgador, date_decision = data_julgamento,
129 | date_publication = data_publicacao, date_registration = data_registro,
130 | rapporteur = relatora, summary = ementa, txt_summary = ts)
131 | }
132 |
--------------------------------------------------------------------------------
/R/utils.R:
--------------------------------------------------------------------------------
1 | #' Pipe operator
2 | #'
3 | #' See \code{\link[magrittr]{\%>\%}} for more details.
4 | #'
5 | #' @name %>%
6 | #' @rdname pipe
7 | #' @keywords internal
8 | #' @importFrom magrittr %>%
9 | NULL
10 |
11 | # Symbols
12 | "!!" <- rlang::`!!`
13 | ":=" <- rlang::`:=`
14 | "%||%" <- purrr::`%||%`
15 |
16 | # Shortcuts for stringr functions
17 | str_replace_all <- stringr::str_replace_all
18 | str_detect <- stringr::str_detect
19 |
20 | # Function for extracting elements from vector given e1 | e2
21 | extract_or <- function(x, e1, e2) {
22 | magrittr::or(e1, e2) %>% magrittr::extract(x, .)
23 | }
24 |
25 | # Convert Portuguese months to number
26 | conv_month <- function(date) {
27 |
28 | # Convert date to more sensible format
29 | date <- stringr::str_replace_all(date, " de ", "-")
30 | month <- stringr::str_extract(date, "[:alpha:]+")
31 |
32 | # Get month number
33 | month <- switch (month,
34 | "janeiro" = "1",
35 | "fevereiro" = "2",
36 | "mar\u00e7o" = "3",
37 | "abril" = "4",
38 | "maio" = "5",
39 | "junho" = "6",
40 | "julho" = "7",
41 | "agosto" = "8",
42 | "setembro" = "9",
43 | "outubro" = "10",
44 | "novembro" = "11",
45 | "dezembro" = "12")
46 |
47 | # Replace name with number
48 | stringr::str_replace(date, "[:alpha:]+", month)
49 | }
50 |
51 | # Convert a date to pt_BR format
52 | date_pt <- function(date) {
53 |
54 | # Check if string is empty
55 | if (stringr::str_length(date) == 0) { return(date) }
56 |
57 | # Apply conversion
58 | date <- lubridate::as_date(date)
59 | stringr::str_c(
60 | stringr::str_pad(lubridate::day(date), 2, "left", "0"),
61 | stringr::str_pad(lubridate::month(date), 2, "left", "0"),
62 | lubridate::year(date),
63 | sep = "/")
64 | }
65 |
66 | # Return time in a human readable way
67 | how_long <- function(x) {
68 |
69 | if (x < 60) {
70 | round(x, 1) %>% stringr::str_c(" seconds")
71 | } else if (x < 3600) {
72 | round(x/60, 1) %>% stringr::str_c(" minutes")
73 | } else if (x < 86400) {
74 | round(x/3600 , 1) %>% stringr::str_c(" hours")
75 | } else if (x < 604800) {
76 | round(x/86400, 1) %>% stringr::str_c(" days")
77 | } else {
78 | round(x/604800, 1) %>% stringr::str_c(" weeks")
79 | }
80 | }
81 |
82 | # Transform an XML tree into a tibble
83 | tree_to_tibble <- function(tree, n = 0) {
84 |
85 | # Extract category names
86 | names <- tree %>%
87 | purrr::map(purrr::pluck, 2, 1) %>%
88 | purrr::compact() %>%
89 | magrittr::extract(. != "") %>%
90 | purrr::flatten_chr()
91 |
92 | # Extract category codes
93 | ids <- tree %>%
94 | purrr::map(purrr::pluck, 2) %>%
95 | purrr::map(attr, "value") %>%
96 | purrr::compact() %>%
97 | magrittr::extract(. != "") %>%
98 | purrr::flatten_chr()
99 |
100 | # Iterate over every branch of tree
101 | purrr::imap_dfr(lengths(tree, FALSE), function(len, i) {
102 |
103 | # If element is a leaf node, return it's contents
104 | # Otherwise recur on it's elements
105 | if (len == 3) {
106 | dplyr::tibble(name5 = names[i], id5 = ids[i])
107 | }
108 | else {
109 | tree %>%
110 | purrr::pluck(i, 4) %>%
111 | magrittr::extract(names(.) == 'li') %>%
112 | tree_to_tibble(n + 1) %>%
113 | dplyr::mutate(
114 | !!stringr::str_c("name", n) := names[i],
115 | !!stringr::str_c("id", n) := ids[i])
116 | }
117 | })
118 | }
119 |
120 | # Remove diacritics (from abjutils)
121 | rm_accent <- function(x) {
122 | if (.Platform$OS.type == 'unix') {
123 | stringr::str_replace_all(iconv(x, to = "ASCII//TRANSLIT"), "[`'\"^~]", "")
124 | } else {
125 | gsub("`", "", iconv(x, from = 'latin1', to="ASCII//TRANSLIT"))
126 | }
127 | }
128 |
129 | # Send message if package is required
130 | require_pkg <- function(package) {
131 |
132 | if (!requireNamespace(package, quietly = TRUE)) {
133 |
134 | if (package == "captchasaj") {
135 | package <- "jtrecenti/captchasaj"
136 | } else if (package == "decryptr") {
137 | package <- "decryptr/decryptr"
138 | }
139 |
140 | msg <- stringr::str_c(
141 | "What you're trying to do requires the ",
142 | package, " package. Please install it.")
143 | stop(msg, call. = FALSE)
144 | }
145 | }
146 |
147 | globalVariables(c(
148 | ".", "Documento", "X1", "X2", "X3", "adv", "arq", "b", "booklet",
149 | "color", "date_link", "desc", "forma", "g", "head", "id",
150 | "info", "key", "link", "n", "n_processo", "nome", "r", "result",
151 | "rm_accent", "setNames", "value", "y", "cd_acordao", "id0", "id5",
152 | "id_processo", "item", "branch", "court", "txt_ementa", "val", "role",
153 | "name", "part", "name0", "name1", "name2", "name3", "name4", "name5",
154 | "class_subject", "comarca", "data_julgamento", "data_registro",
155 | "ementa", "id_decision", "id_lawsuit", "id_page", "orgao_julgador",
156 | "relatora", "txt_summary", "hidden", "data_publicacao", "Data",
157 | "Movimento", "movement", "description", "assunto", "classe",
158 | "data_de_disponibilizacao", "foro", "magistrado", "vara", "min_pag"))
159 |
--------------------------------------------------------------------------------
/docs/reference/run_parser.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
122 |
123 |
128 |
93 |
105 |
111 |
112 |
113 |
114 |
121 |
94 |
96 |
97 |
98 | Parses decisions
95 |Parses decisions
99 | 100 | 101 |parse_decisions(parser)102 | 103 |
Arguments
104 || parser | 108 |A parser returned by |
109 |
|---|
37 |
38 |
87 |
88 |
89 |
90 |
91 |
141 |
142 |
143 |
144 |
--------------------------------------------------------------------------------
/docs/reference/peek_cjpg.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
134 |
135 |
140 |
93 |
105 |
123 |
124 |
125 |
126 |
133 |
94 |
96 |
97 |
98 | Runs a parser
95 |Runs a parser
99 | 100 | 101 |run_parser(file, parser, path = ".", cores = 1)102 | 103 |
Arguments
104 || file | 108 |A character vector with the paths to one ore more files |
109 |
|---|---|
| parser | 112 |A parser returned by |
113 |
| path | 116 |The path to a directory where to save RDSs |
117 |
| cores | 120 |The number of cores to be used when parsing |
121 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
136 |
137 |
138 |
139 |
--------------------------------------------------------------------------------
/docs/reference/peek_cjsg.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
129 |
130 |
135 |
93 |
105 |
112 |
113 |
119 |
128 |
94 | Check how long a call to
95 |
96 |
97 |
98 | Check how long a call to download_cjpg() will probably take
95 | Check how long a call to download_cjpg() will probably take
peek_cjpg(...)102 | 103 |
Arguments
104 || ... | 108 |Arguments passed on to |
110 |
|---|
See also
114 | 115 | 116 | 117 | 118 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
136 |
137 |
138 |
139 |
--------------------------------------------------------------------------------
/R/cjpg_table.R:
--------------------------------------------------------------------------------
1 |
2 | #' @title Download information about some of CJPG's structures
3 | #'
4 | #' @description Downloads a table with information about lawsuit's
5 | #' classes, subjects or courts to help with [download_cjpg()]. You
6 | #' can also browse some of these tables with [browse_table()].
7 | #'
8 | #' @param type Either `"classes"` or `"subjects"` or `"courts"`
9 | #' @param tj TJ from which to get data (only works with TJSP for now)
10 | #' @return A tibble with either 12 columns (if `type` is `"classes"`
11 | #' or `"subjects"`) or 3 columns (if `type` is `"courts"`)
12 | #'
13 | #' @seealso [download_cjpg()], [browse_table()]
14 | #' @export
15 | cjpg_table <- function(type, tj = "tjsp") {
16 |
17 | # Stop if TJ isn't TJSP
18 | stopifnot(tj == "tjsp")
19 |
20 | # If type is courts, redirect
21 | if (type == "courts") { return(cjpg_courts()) }
22 |
23 | # Translate type
24 | type <- switch (type,
25 | classes = "classe",
26 | subjects = "assunto")
27 |
28 | # Fetch table with information
29 | stringr::str_c(
30 | "https://esaj.tjsp.jus.br/cjpg/", type,
31 | "TreeSelect.do?campoId=", type) %>%
32 | httr::GET(httr::config(ssl_verifypeer = FALSE)) %>%
33 | httr::content('text') %>%
34 | xml2::read_html() %>%
35 | xml2::xml_find_all("//div[@class='treeView']") %>%
36 | purrr::modify(xml2::as_list) %>%
37 | dplyr::first() %>% dplyr::nth(2) %>%
38 | purrr::keep(~is.list(.x)) %>%
39 | tree_to_tibble() %>%
40 | dplyr::mutate(
41 | name0 = ifelse(is.na(name0), name5, name0),
42 | id0 = ifelse(is.na(id0), id5, id0)) %>%
43 | dplyr::select(
44 | dplyr::ends_with('0'), dplyr::ends_with('1'),
45 | dplyr::ends_with('2'), dplyr::ends_with('3'),
46 | dplyr::ends_with('4'), dplyr::ends_with('5'))
47 | }
48 |
49 | # Download table with court information for [cjpg_table()]
50 | cjpg_courts <- function() {
51 |
52 | # Function for creating the rows of the table
53 | create_row <- function(x) {
54 |
55 | # XPaths
56 | xp_parent <- ".//span[contains(@id, 'varas_tree')]"
57 | xp_child <- ".//li[@class='leafItem']//span[contains(@id, 'varas_tree')]"
58 |
59 | # Create row
60 | branch <- x %>%
61 | rvest::html_node(xpath = xp_parent) %>%
62 | rvest::html_text()
63 | x %>%
64 | rvest::html_nodes(xpath = xp_child) %>%
65 | purrr::map(~tibble::tibble(
66 | id = rvest::html_attr(.x, 'value'),
67 | court = rvest::html_text(.x))) %>%
68 | dplyr::bind_rows() %>%
69 | dplyr::mutate(branch = branch)
70 | }
71 |
72 | # Create courts table
73 | stringr::str_c(
74 | "https://esaj.tjsp.jus.br/cjpg/",
75 | "varasTreeSelect.do?campoId=varas") %>%
76 | httr::GET(httr::config(ssl_verifypeer = FALSE)) %>%
77 | httr::content('text') %>%
78 | xml2::read_html() %>%
79 | rvest::html_nodes('li.open') %>%
80 | rlang::as_list() %>%
81 | purrr::modify(create_row) %>%
82 | dplyr::bind_rows() %>%
83 | dplyr::select(branch, court, id)
84 | }
85 |
86 | #' @title Browse table returned by [cjpg_table()] or [cjsg_table()]
87 | #'
88 | #' @description This function uses a list of regex to filter CJPG
89 | #' and CJSG tables (only if they are of type `"classes"` or
90 | #' `"subjects"`) more easily than with `dplyr::select()`. For
91 | #' details on how the matching occurs, see **Matching**.
92 | #'
93 | #' @section Matching: For the matching to work properly, `patterns`
94 | #' should be a list of at most 6 character vectors, each one
95 | #' containing either one or a vector of regular expressions to
96 | #' be applied from left to right on columns `name0` to `name5`
97 | #' (note that vectors are ORed and different elements are ANDed).
98 | #' Example: If `patterns` looks something like
99 | #' `list(c("ADM", "CRIMINAL"), "", "", "", "", "Recurso")`,
100 | #' then we'll get back the rows where `name0` contains "ADM"
101 | #' **or** "CRIMINAL" **and** where `name5` contains "Recurso".
102 | #'
103 | #' @param table Table returned by [cjpg_table()] or [cjsg_table()]
104 | #' (only valid for `"classes"` or `"subjects"` types)
105 | #' @param patterns A list containing (at most) 6 character vectors
106 | #' of one or more regular expressions (applied from left to right
107 | #' on `name0` to `name5`), e.g.,
108 | #' `list(c("ADM", "CRIMINAL"), "", "", "", "", "Recurso")`
109 | #' @return The original table filtered according to `patterns`
110 | #'
111 | #' @seealso [cjpg_table()], [cjsg_table()]
112 | #' @export
113 | browse_table <- function(table, patterns) {
114 |
115 | patterns <- purrr::modify(patterns, function(pat) {
116 | pat %>%
117 | stringr::str_c(collapse = "|") %>%
118 | stringr::str_c("(?:", ., ")") %>%
119 | stringr::str_replace("\\(\\?\\:\\)", "")
120 | })
121 |
122 | # Transform NAs into matches
123 | str_detect <- function(string, pattern) {
124 | stringr::str_detect(string, pattern) %>%
125 | magrittr::inset(is.na(.) && pattern == "", TRUE)
126 | }
127 |
128 | # Apply filters
129 | table %>%
130 | dplyr::filter(
131 | str_detect(name0, patterns[[1]]),
132 | str_detect(name1, patterns[[2]]),
133 | str_detect(name2, patterns[[3]]),
134 | str_detect(name3, patterns[[4]]),
135 | str_detect(name4, patterns[[5]]),
136 | str_detect(name5, patterns[[6]]))
137 | }
138 |
--------------------------------------------------------------------------------
/docs/reference/download_decision.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
129 |
130 |
135 |
93 |
105 |
112 |
113 |
119 |
128 |
94 | Check how long a call to
95 |
96 |
97 |
98 | Check how long a call to download_cjsg() will probably take
95 | Check how long a call to download_cjsg() will probably take
peek_cjsg(...)102 | 103 |
Arguments
104 || ... | 108 |Arguments passed on to |
110 |
|---|
See also
114 | 115 | 116 | 117 | 118 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
145 |
146 |
147 |
148 |
--------------------------------------------------------------------------------
/docs/pkgdown.css:
--------------------------------------------------------------------------------
1 | img.icon {
2 | float: left;
3 | margin-left: -35px;
4 | width: 30px;
5 | height: 30px;
6 | }
7 |
8 | body {font-size: 16px;}
9 | h1 {font-size: 40px;}
10 | h2 {font-size: 30px;}
11 |
12 | /* Fixes for fixed navbar --------------------------*/
13 |
14 | body {
15 | position: relative;
16 | padding-top: 65px;
17 | }
18 |
19 | .contents h1, .contents h2, .contents h3, .contents h4 {
20 | padding-top: 65px;
21 | margin-top: -45px;
22 | }
23 |
24 | .page-header {
25 | margin-top: 0;
26 | margin-bottom: 10px;
27 | padding-bottom: 0px;
28 | }
29 |
30 | /* Static header placement on mobile devices */
31 | @media (max-width: 767px) {
32 | .navbar-fixed-top {
33 | position: absolute;
34 | }
35 | }
36 |
37 | .navbar-toggle {
38 | margin-top: 8px;
39 | margin-bottom: 5px;
40 | }
41 |
42 | .navbar-nav li a {
43 | padding-bottom: 10px;
44 | }
45 | .navbar-default .navbar-nav > .active > a,
46 | .navbar-default .navbar-nav > .active > a:hover,
47 | .navbar-default .navbar-nav > .active > a:focus {
48 | background-color: #eee;
49 | }
50 |
51 | /* Table of contents --------------------------*/
52 |
53 | #sidebar {
54 | /*
55 | Needed to avoid bug in sticky-kit:
56 | https://github.com/leafo/sticky-kit/issues/169
57 | */
58 | position:static;
59 | }
60 |
61 | #sidebar h2 {
62 | font-size: 1.6em;
63 | margin-top: 1em;
64 | margin-bottom: 0.25em;
65 | }
66 |
67 | #sidebar .list-unstyled li {
68 | margin-bottom: 0.5em;
69 | line-height: 1.4;
70 | }
71 |
72 | #sidebar small {
73 | color: #777;
74 | }
75 |
76 | /* Syntax highlighting ---------------------------------------------------- */
77 |
78 | pre {
79 | word-wrap: normal;
80 | word-break: normal;
81 | border: none;
82 | }
83 |
84 | pre, code {
85 | background-color: #fafafa;
86 | color: #000000;
87 | -webkit-font-smoothing: subpixel-antialiased;
88 | }
89 |
90 | pre img {
91 | background-color: #fff;
92 | display: block;
93 | }
94 |
95 | code a, pre a {
96 | color: #375f84;
97 | }
98 |
99 | .fl {color: #1514b5;}
100 | .fu {color: #000000;} /* function */
101 | .ch,.st {color: #036a07;} /* string */
102 | .kw {color: #264D66;} /* keyword */
103 | .co {color: #777777;} /* comment */
104 |
105 | .message { color: black; font-weight: bolder;}
106 | .error { color: orange; font-weight: bolder;}
107 | .warning { color: orange; font-weight: normal;}
108 |
109 |
110 | /* Status --------------------------- */
111 |
112 | .status-container {
113 | padding-top:32px;
114 | }
115 |
116 | .status-container a {
117 | display: block;
118 | margin-bottom: 5px;
119 | }
120 |
121 | /* For shrinking navbar ------------------ */
122 |
123 | /* For big header
124 |
125 | &-brand {
126 | font-family: $font-family-monospace;
127 | font-weight: normal;
128 | font-size: 48px;
129 | padding: 35px 15px;
130 |
131 | padding-left: 84px;
132 | background-image:url(../logo.png);
133 | background-size: 60px auto;
134 | background-repeat: no-repeat;
135 | background-position: 15px center;
136 |
137 | }
138 | */
139 |
140 | /* Reference index & topics ----------------------------------------------- */
141 |
142 | .ref-index th {font-weight: normal;}
143 | .ref-index h2 {font-size: 20px;}
144 |
145 | .ref-index td {vertical-align: top;}
146 | .ref-index .alias {width: 40%;}
147 | .ref-index .title {width: 60%;}
148 |
149 | .ref-index .alias {width: 40%;}
150 | .ref-index .title {width: 60%;}
151 |
152 | .ref-arguments th {text-align: right; padding-right: 10px;}
153 | .ref-arguments th, .ref-arguments td {vertical-align: top;}
154 | .ref-arguments .name {width: 10%;}
155 | .ref-arguments .desc {width: 90%;}
156 |
157 | /* For the rstudio footer ------- */
158 |
159 | footer {
160 | margin-top: 45px;
161 | padding: 35px 0 36px;
162 | border-top: 1px solid #e5e5e5;
163 |
164 | display: flex;
165 | color: #666;
166 | }
167 | footer p {
168 | margin-bottom: 0;
169 | }
170 | footer .tidyverse {
171 | flex: 1;
172 | }
173 | footer .author {
174 | flex: 1;
175 | text-align: right;
176 | }
177 |
178 | /* ---------------------- hover anchor tags */
179 |
180 | .hasAnchor {
181 | margin-left: -30px;
182 | }
183 |
184 | a.anchor {
185 | display:inline-block;
186 | width: 30px;
187 | height: 30px;
188 | visibility: hidden;
189 |
190 | background-image: url(./link.svg);
191 | background-repeat: no-repeat;
192 | background-size: 20px 20px;
193 | background-position: center center;
194 | }
195 |
196 | .hasAnchor:hover a.anchor {
197 | visibility: visible;
198 | }
199 |
200 | @media (max-width: 767px) {
201 | .hasAnchor {margin-left: 0;}
202 | a.anchor {float: right;}
203 | }
204 |
205 | /* Tweak appearance of navigation in sidebar ---------------------- */
206 |
207 | #sidebar .nav {
208 | padding-left: 0px;
209 | list-style-type: none;
210 | color: #5a9ddb;
211 | }
212 |
213 | #sidebar .nav > li {
214 | padding: 10px 0 0px 20px;
215 | display: list-item;
216 | line-height: 20px;
217 | background-image: url(./tocBullet.svg);
218 | background-repeat: no-repeat;
219 | background-size: 16px 280px;
220 | background-position: left 0px;
221 | }
222 |
223 | #sidebar .nav > li.active {
224 | background-position: left -240px;
225 | }
226 |
227 | #sidebar a {
228 | padding: 0px;
229 | color: #5a9ddb;
230 | background-color: transparent;
231 | }
232 |
233 | #sidebar a:hover {
234 | background-color: transparent;
235 | text-decoration: underline;
236 | }
237 |
--------------------------------------------------------------------------------
/docs/reference/download_2deg_lawsuit.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
138 |
139 |
144 |
93 |
107 |
121 |
122 |
128 |
137 |
94 |
96 |
97 |
98 | Download PDFs corresponding to judicial decisions
95 |Given the unique identifier of a judicial decision 99 | (an 8 digit number), this function downloads the corresponding 100 | PDF.
101 | 102 | 103 |download_decision(decision, path = ".", tj = "tjsp")104 | 105 |
Arguments
106 || decision | 110 |A character vector with decision IDs |
111 |
|---|---|
| path | 114 |Path to directory where to save PDF |
115 |
| tj | 118 |TJ from which to get data (only works with TJSP for now) |
119 |
Value
123 | 124 |A character vector with the path to the downloaded file
125 | 126 | 127 |
37 |
38 |
69 |
70 |
71 |
72 |
73 |
145 |
146 |
147 |
148 |
--------------------------------------------------------------------------------
/docs/reference/download_lawsuit.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
74 |
138 |
139 |
144 |
75 |
89 |
100 |
101 |
124 |
137 |
76 |
78 |
79 |
80 | Download second degree lawsuits filed in Brazilian Justice Courts
77 |This function downloads lawsuits as PDFs. Given a lawsuit ID, and 81 | the path to a directory it will collect the lawsuit, and save it to 82 | the provided directory.
83 | 84 | 85 |download_2deg_lawsuit(id, path = ".")86 | 87 |
Arguments
88 || id | 92 |A character vector of one or more lawsuit IDs (only works with 93 | TJSP for now) |
94 |
|---|---|
| path | 97 |Path to the directory where the lawsuit should be saved |
98 |
Value
102 | 103 |A character vector with the path to the downloaded lawsuit
104 | 105 |About lawsuits
106 | 107 | 108 |The lawsuits contemplated by this funtion have to be filed in a
109 | Brazilian Tribunal de Justica (Justice Court). download_2deg_lawsuit()
110 | finds the lawsuit in its state's online Sistema de Automacao de Justica
111 | (Justice Automation System), solves the captcha withholding the
112 | information, and collects the PDF.
Implemented TJs
115 | 116 | 117 |Unfortunatelly download_2deg_lawsuit() doesn't yet work with all 27
118 | TJs in Brazil. Here are the ones already implemented:
-
119 |
TJSP (Sao Paulo)
120 |
37 |
38 |
69 |
70 |
71 |
72 |
73 |
147 |
148 |
149 |
150 |
--------------------------------------------------------------------------------
/docs/reference/cjpg_table.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
74 |
140 |
141 |
146 |
75 |
89 |
99 |
100 |
126 |
139 |
76 |
78 |
79 |
80 | Download first degree lawsuits filed in Brazilian Justice Courts
77 |This function downloads lawsuits as PDFs. Given a lawsuit ID, and 81 | the path to a directory it will collect the lawsuit, and save it to 82 | the provided directory.
83 | 84 | 85 |download_lawsuit(id, path = ".")86 | 87 |
Arguments
88 || id | 92 |A character vector of one or more lawsuit IDs |
93 |
|---|---|
| path | 96 |Path to the directory where the lawsuit should be saved |
97 |
Value
101 | 102 |A character vector with the path to the downloaded lawsuit
103 | 104 |About lawsuits
105 | 106 | 107 |The lawsuits contemplated by this funtion have to be filed in a
108 | Brazilian Tribunal de Justica (Justice Court). download_lawsuit()
109 | finds the lawsuit in its state's online Sistema de Automacao de Justica
110 | (Justice Automation System), solves the captcha withholding the
111 | information, and collects the PDF.
Implemented TJs
114 | 115 | 116 |Unfortunatelly download_lawsuit() doesn't yet work with all 27 TJs in
117 | Brazil. Here are the ones already implemented:
-
118 |
TJAM (Amazonas)
119 | TJBA (Bahia)
120 | TJSC (Santa Catarina)
121 | TJSP (Sao Paulo)
122 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
148 |
149 |
150 |
151 |
--------------------------------------------------------------------------------
/docs/reference/cjsg_table.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
141 |
142 |
147 |
93 |
107 |
117 |
118 |
129 |
140 |
94 |
96 |
97 |
98 | Download information about some of CJPG's structures
95 |Downloads a table with information about lawsuit's
99 | classes, subjects or courts to help with download_cjpg(). You
100 | can also browse some of these tables with browse_table().
cjpg_table(type, tj = "tjsp")104 | 105 |
Arguments
106 || type | 110 |Either |
111 |
|---|---|
| tj | 114 |TJ from which to get data (only works with TJSP for now) |
115 |
Value
119 | 120 |A tibble with either 12 columns (if type is "classes"
121 | or "subjects") or 3 columns (if type is "courts")
See also
124 | 125 | 126 | 127 | 128 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
148 |
149 |
150 |
151 |
--------------------------------------------------------------------------------
/docs/reference/parse_cjpg.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
141 |
142 |
147 |
93 |
107 |
117 |
118 |
129 |
140 |
94 |
96 |
97 |
98 | Download information about some of CJSG's structures
95 |Downloads a table with information about lawsuit's
99 | classes, subjects or courts to help with download_cjsg(). You
100 | can also browse some of these tables with browse_table().
cjsg_table(type, tj = "tjsp")104 | 105 |
Arguments
106 || type | 110 |Either |
111 |
|---|---|
| tj | 114 |TJ from which to get data (only works with TJSP for now) |
115 |
Value
119 | 120 |A tibble with either 12 columns (if type is "classes"
121 | or "subjects") or 3 columns (if type is "courts")
See also
124 | 125 | 126 | 127 | 128 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
150 |
151 |
152 |
153 |
--------------------------------------------------------------------------------
/docs/reference/parse_cjsg.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
92 |
143 |
144 |
149 |
93 |
105 |
111 |
112 |
133 |
142 |
94 |
96 |
97 |
98 | CJPG parser
95 |Parser for files downloaded by download_cjpg().
parse_cjpg(arqs)102 | 103 |
Arguments
104 || arqs | 108 |Character vector with the paths of the files to be parsed |
109 |
|---|
Value
113 | 114 |A tibble with the columns
-
115 |
arqName of the file
116 | idID found in the page read
117 | cd_acordaoUnique ID of the ruling
118 | n_processoNumber of the lawsuit (doesn't have to be unique)
119 | comarcaName of the district
120 | data_julgamentoDate of the judgement (%d/%m/%Y)
121 | data_registroDate of registration in the system (%d/%m/%Y)
122 | ementaSummary of the ruling
123 | orgao_julgadorBody responsible for the appeal
124 | outros_numerosOld/additional IDs
125 | relatoraName of the rapporteur
126 | classe_assuntoClass/subject, separated by slashes
127 | txt_ementaText of the summary with no formatting
128 |
37 |
38 |
87 |
88 |
89 |
90 |
91 |
150 |
151 |
152 |
153 |
--------------------------------------------------------------------------------
92 |
143 |
144 |
149 |
93 |
105 |
111 |
112 |
133 |
142 |
94 |
96 |
97 |
98 | CJSG parser
95 |Parser for files downloaded by download_cjsg().
parse_cjsg(arqs)102 | 103 |
Arguments
104 || arqs | 108 |Character vector with the paths of the files to be parsed |
109 |
|---|
Value
113 | 114 |A tibble with the columns
-
115 |
arqName of the file
116 | idID found in the page read
117 | cd_acordaoUnique ID of the ruling
118 | n_processoNumber of the lawsuit (doesn't have to be unique)
119 | comarcaName of the district
120 | data_julgamentoDate of the judgement (%d/%m/%Y)
121 | data_registroDate of registration in the system (%d/%m/%Y)
122 | ementaSummary of the ruling
123 | orgao_julgadorBody responsible for the appeal
124 | outros_numerosOld/additional IDs
125 | relatoraName of the rapporteur
126 | classe_assuntoClass/subject, separated by slashes
127 | txt_ementaText of the summary with no formatting
128 |