1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
|
#' Read HTML or XML.
#'
#' @section Setting the "user agent" header:
#'
#' When performing web scraping tasks it is both good practice --- and often required ---
#' to set the [user agent](https://en.wikipedia.org/wiki/User_agent) request header
#' to a specific value. Sometimes this value is assigned to emulate a browser in order
#' to have content render in a certain way (e.g. `Mozilla/5.0 (Windows NT 5.1; rv:52.0)
#' Gecko/20100101 Firefox/52.0` to emulate more recent Windows browsers). Most often,
#' this value should be set to provide the web resource owner information on who you are
#' and the intent of your actions like this Google scraping bot user agent identifier:
#' `Googlebot/2.1 (+http://www.google.com/bot.html)`.
#'
#' You can set the HTTP user agent for URL-based requests using [httr::set_config()] and [httr::user_agent()]:
#'
#' `httr::set_config(httr::user_agent("me@@example.com; +https://example.com/info.html"))`
#'
#' [httr::set_config()] changes the configuration globally,
#' [httr::with_config()] can be used to change configuration temporarily.
#'
#' @param x A string, a connection, or a raw vector.
#'
#' A string can be either a path, a url or literal xml. Urls will
#' be converted into connections either using `base::url` or, if
#' installed, `curl::curl`. Local paths ending in `.gz`,
#' `.bz2`, `.xz`, `.zip` will be automatically uncompressed.
#'
#' If a connection, the complete connection is read into a raw vector before
#' being parsed.
#' @param encoding Specify a default encoding for the document. Unless
#' otherwise specified XML documents are assumed to be in UTF-8 or
#' UTF-16. If the document is not UTF-8/16, and lacks an explicit
#' encoding directive, this allows you to supply a default.
#' @param ... Additional arguments passed on to methods.
#' @param as_html Optionally parse an xml file as if it's html.
#' @param base_url When loading from a connection, raw vector or literal
#' html/xml, this allows you to specify a base url for the document. Base
#' urls are used to turn relative urls into absolute urls.
#' @param n If `file` is a connection, the number of bytes to read per
#' iteration. Defaults to 64kb.
#' @param verbose When reading from a slow connection, this prints some
#' output on every iteration so you know its working.
#' @param options Set parsing options for the libxml2 parser. Zero or more of
#' \Sexpr[results=rd, stage=build]{xml2:::describe_options(xml2:::xml_parse_options())}
#' @return An XML document. HTML is normalised to valid XML - this may not
#' be exactly the same transformation performed by the browser, but it's
#' a reasonable approximation.
#' @export
#' @examples
#' # Literal xml/html is useful for small examples
#' read_xml("<foo><bar /></foo>")
#' read_html("<html><title>Hi<title></html>")
#' read_html("<html><title>Hi")
#'
#' # From a local path
#' read_html(system.file("extdata", "r-project.html", package = "xml2"))
#'
#' \dontrun{
#' # From a url
#' cd <- read_xml(xml2_example("cd_catalog.xml"))
#' me <- read_html("http://had.co.nz")
#' }
read_xml <- function(x, encoding = "", ..., as_html = FALSE, options = "NOBLANKS") {
UseMethod("read_xml")
}
#' @export
#' @rdname read_xml
read_html <- function(x,
encoding = "",
...,
options = c("RECOVER", "NOERROR", "NOBLANKS", "HUGE")) {
UseMethod("read_html")
}
#' @export
read_html.default <- function(x,
encoding = "",
...,
options = c("RECOVER", "NOERROR", "NOBLANKS", "HUGE")) {
options <- parse_options(options, xml_parse_options())
suppressWarnings(read_xml(x, encoding = encoding, ..., as_html = TRUE, options = options))
}
#' @export
read_html.response <- function(x,
encoding = "",
options = c("RECOVER", "NOERROR", "NOBLANKS"),
...) {
check_installed("httr")
options <- parse_options(options, xml_parse_options())
httr::stop_for_status(x)
content <- httr::content(x, as = "raw")
xml2::read_html(content, encoding = encoding, options = options, ...)
}
#' @export
#' @rdname read_xml
read_xml.character <- function(x,
encoding = "",
...,
as_html = FALSE,
options = "NOBLANKS") {
check_string(x)
options <- parse_options(options, xml_parse_options())
if (grepl("<|>", x)) {
read_xml.raw(charToRaw(enc2utf8(x)), "UTF-8", ..., as_html = as_html, options = options)
} else {
con <- path_to_connection(x)
if (inherits(con, "connection")) {
read_xml.connection(con,
encoding = encoding, ..., as_html = as_html,
base_url = x, options = options
)
} else {
doc <- .Call(doc_parse_file, con,
encoding = encoding, as_html = as_html,
options = options
)
xml_document(doc)
}
}
}
#' @export
#' @rdname read_xml
read_xml.raw <- function(x,
encoding = "",
base_url = "",
...,
as_html = FALSE,
options = "NOBLANKS") {
options <- parse_options(options, xml_parse_options())
doc <- .Call(doc_parse_raw, x, encoding, base_url, as_html, options)
xml_document(doc)
}
#' @export
#' @rdname read_xml
read_xml.connection <- function(x,
encoding = "",
n = 64 * 1024,
verbose = FALSE,
...,
base_url = "",
as_html = FALSE,
options = "NOBLANKS") {
options <- parse_options(options, xml_parse_options())
if (!isOpen(x)) {
open(x, "rb")
on.exit(close(x))
}
raw <- .Call(read_connection_, x, n)
read_xml.raw(raw,
encoding = encoding, base_url = base_url, as_html =
as_html, options = options
)
}
#' @export
read_xml.response <- function(x,
encoding = "",
base_url = "",
...,
as_html = FALSE,
options = "NOBLANKS") {
check_installed("httr")
options <- parse_options(options, xml_parse_options())
httr::stop_for_status(x)
content <- httr::content(x, as = "raw")
xml2::read_xml(content,
encoding = encoding, base_url = if (nzchar(base_url)) base_url else x$url,
as_html = as_html, option = options, ...
)
}
#' @export
read_xml.textConnection <- function(x,
encoding = "",
...) {
s <- paste(readLines(x), collapse = "\n")
read_xml.character(s, ...)
}
#' Download a HTML or XML file
#'
#' Libcurl implementation of `C_download` (the "internal" download method)
#' with added support for https, ftps, gzip, etc. Default behavior is identical
#' to [download.file()], but request can be fully configured by passing
#' a custom [curl::handle()].
#' @inherit curl::curl_download
#' @param file A character string with the name where the downloaded file is
#' saved.
#' @seealso [curl_download][curl::curl_download]
#' @export
#' @examples
#' \dontrun{
#' download_html("http://tidyverse.org/index.html")
#' }
download_xml <- function(url,
file = basename(url),
quiet = TRUE,
mode = "wb",
handle = curl::new_handle()) {
check_installed("curl", "to use `download_xml()`.")
curl::curl_download(url, file, quiet = quiet, mode = mode, handle = handle)
invisible(file)
}
#' @export
#' @rdname download_xml
download_html <- download_xml
|
