diff options
Diffstat (limited to 'vendor/github.com/PuerkitoBio')
| -rw-r--r-- | vendor/github.com/PuerkitoBio/goquery/README.md | 37 | ||||
| -rw-r--r-- | vendor/github.com/PuerkitoBio/goquery/array.go | 25 | ||||
| -rw-r--r-- | vendor/github.com/PuerkitoBio/goquery/expand.go | 24 | ||||
| -rw-r--r-- | vendor/github.com/PuerkitoBio/goquery/manipulation.go | 7 | ||||
| -rw-r--r-- | vendor/github.com/PuerkitoBio/goquery/query.go | 6 | ||||
| -rw-r--r-- | vendor/github.com/PuerkitoBio/goquery/type.go | 12 |
6 files changed, 96 insertions, 15 deletions
diff --git a/vendor/github.com/PuerkitoBio/goquery/README.md b/vendor/github.com/PuerkitoBio/goquery/README.md index f5ad147..5e899d4 100644 --- a/vendor/github.com/PuerkitoBio/goquery/README.md +++ b/vendor/github.com/PuerkitoBio/goquery/README.md @@ -1,7 +1,6 @@ # goquery - a little like that j-thing, only in Go [](http://travis-ci.org/PuerkitoBio/goquery) [](http://godoc.org/github.com/PuerkitoBio/goquery) [](https://sourcegraph.com/github.com/PuerkitoBio/goquery?badge) - goquery brings a syntax and a set of features similar to [jQuery][] to the [Go language][go]. It is based on Go's [net/html package][html] and the CSS Selector library [cascadia][]. Since the net/html parser returns nodes, and not a full-featured DOM tree, jQuery's stateful manipulation functions (like height(), css(), detach()) have been left off. Also, because the net/html parser requires UTF-8 encoding, so does goquery: it is the caller's responsibility to ensure that the source document provides UTF-8 encoded HTML. See the [wiki][] for various options to do this. @@ -15,6 +14,7 @@ Syntax-wise, it is as close as possible to jQuery, with the same function names * [API](#api) * [Examples](#examples) * [Related Projects](#related-projects) +* [Support](#support) * [License](#license) ## Installation @@ -37,6 +37,10 @@ Please note that because of the net/html dependency, goquery requires Go1.1+. **Note that goquery's API is now stable, and will not break.** +* **2018-06-07 (v1.4.1)** : Add `NewDocumentFromReader` examples. +* **2018-03-24 (v1.4.0)** : Deprecate `NewDocument(url)` and `NewDocumentFromResponse(response)`. +* **2018-01-28 (v1.3.0)** : Add `ToEnd` constant to `Slice` until the end of the selection (thanks to @davidjwilkins for raising the issue). +* **2018-01-11 (v1.2.0)** : Add `AddBack*` and deprecate `AndSelf` (thanks to @davidjwilkins). * **2017-02-12 (v1.1.0)** : Add `SetHtml` and `SetText` (thanks to @glebtv). * **2016-12-29 (v1.0.2)** : Optimize allocations for `Selection.Text` (thanks to @radovskyb). * **2016-08-28 (v1.0.1)** : Optimize performance for large documents. @@ -92,12 +96,24 @@ package main import ( "fmt" "log" + "net/http" "github.com/PuerkitoBio/goquery" ) func ExampleScrape() { - doc, err := goquery.NewDocument("http://metalsucks.net") + // Request the HTML page. + res, err := http.Get("http://metalsucks.net") + if err != nil { + log.Fatal(err) + } + defer res.Body.Close() + if res.StatusCode != 200 { + log.Fatalf("status code error: %d %s", res.StatusCode, res.Status) + } + + // Load the HTML document + doc, err := goquery.NewDocumentFromReader(res.Body) if err != nil { log.Fatal(err) } @@ -122,6 +138,23 @@ func main() { - [andybalholm/cascadia][cascadia], the CSS selector library used by goquery. - [suntong/cascadia][cascadiacli], a command-line interface to the cascadia CSS selector library, useful to test selectors. - [asciimoo/colly](https://github.com/asciimoo/colly), a lightning fast and elegant Scraping Framework +- [gnulnx/goperf](https://github.com/gnulnx/goperf), a website performance test tool that also fetches static assets. + +## Support + +There are a number of ways you can support the project: + +* Use it, star it, build something with it, spread the word! + - If you do build something open-source or otherwise publicly-visible, let me know so I can add it to the [Related Projects](#related-projects) section! +* Raise issues to improve the project (note: doc typos and clarifications are issues too!) + - Please search existing issues before opening a new one - it may have already been adressed. +* Pull requests: please discuss new code in an issue first, unless the fix is really trivial. + - Make sure new code is tested. + - Be mindful of existing code - PRs that break existing code have a high probability of being declined, unless it fixes a serious issue. + +If you desperately want to send money my way, I have a BuyMeACoffee.com page: + +<a href="https://www.buymeacoffee.com/mna" target="_blank"><img src="https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png" alt="Buy Me A Coffee" style="height: 41px !important;width: 174px !important;box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;-webkit-box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;" ></a> ## License diff --git a/vendor/github.com/PuerkitoBio/goquery/array.go b/vendor/github.com/PuerkitoBio/goquery/array.go index d7af5ee..1b1f6cb 100644 --- a/vendor/github.com/PuerkitoBio/goquery/array.go +++ b/vendor/github.com/PuerkitoBio/goquery/array.go @@ -4,6 +4,16 @@ import ( "golang.org/x/net/html" ) +const ( + maxUint = ^uint(0) + maxInt = int(maxUint >> 1) + + // ToEnd is a special index value that can be used as end index in a call + // to Slice so that all elements are selected until the end of the Selection. + // It is equivalent to passing (*Selection).Length(). + ToEnd = maxInt +) + // First reduces the set of matched elements to the first in the set. // It returns a new Selection object, and an empty Selection object if the // the selection is empty. @@ -35,12 +45,23 @@ func (s *Selection) Eq(index int) *Selection { } // Slice reduces the set of matched elements to a subset specified by a range -// of indices. +// of indices. The start index is 0-based and indicates the index of the first +// element to select. The end index is 0-based and indicates the index at which +// the elements stop being selected (the end index is not selected). +// +// The indices may be negative, in which case they represent an offset from the +// end of the selection. +// +// The special value ToEnd may be specified as end index, in which case all elements +// until the end are selected. This works both for a positive and negative start +// index. func (s *Selection) Slice(start, end int) *Selection { if start < 0 { start += len(s.Nodes) } - if end < 0 { + if end == ToEnd { + end = len(s.Nodes) + } else if end < 0 { end += len(s.Nodes) } return pushStack(s, s.Nodes[start:end]) diff --git a/vendor/github.com/PuerkitoBio/goquery/expand.go b/vendor/github.com/PuerkitoBio/goquery/expand.go index f0c6c86..7caade5 100644 --- a/vendor/github.com/PuerkitoBio/goquery/expand.go +++ b/vendor/github.com/PuerkitoBio/goquery/expand.go @@ -41,6 +41,30 @@ func (s *Selection) AddNodes(nodes ...*html.Node) *Selection { // AndSelf adds the previous set of elements on the stack to the current set. // It returns a new Selection object containing the current Selection combined // with the previous one. +// Deprecated: This function has been deprecated and is now an alias for AddBack(). func (s *Selection) AndSelf() *Selection { + return s.AddBack() +} + +// AddBack adds the previous set of elements on the stack to the current set. +// It returns a new Selection object containing the current Selection combined +// with the previous one. +func (s *Selection) AddBack() *Selection { return s.AddSelection(s.prevSel) } + +// AddBackFiltered reduces the previous set of elements on the stack to those that +// match the selector string, and adds them to the current set. +// It returns a new Selection object containing the current Selection combined +// with the filtered previous one +func (s *Selection) AddBackFiltered(selector string) *Selection { + return s.AddSelection(s.prevSel.Filter(selector)) +} + +// AddBackMatcher reduces the previous set of elements on the stack to those that match +// the mateher, and adds them to the curernt set. +// It returns a new Selection object containing the current Selection combined +// with the filtered previous one +func (s *Selection) AddBackMatcher(m Matcher) *Selection { + return s.AddSelection(s.prevSel.FilterMatcher(m)) +} diff --git a/vendor/github.com/PuerkitoBio/goquery/manipulation.go b/vendor/github.com/PuerkitoBio/goquery/manipulation.go index ebb4ffe..34eb757 100644 --- a/vendor/github.com/PuerkitoBio/goquery/manipulation.go +++ b/vendor/github.com/PuerkitoBio/goquery/manipulation.go @@ -270,13 +270,14 @@ func (s *Selection) ReplaceWithNodes(ns ...*html.Node) *Selection { return s.Remove() } -// Set the html content of each element in the selection to specified html string. +// SetHtml sets the html content of each element in the selection to +// specified html string. func (s *Selection) SetHtml(html string) *Selection { return setHtmlNodes(s, parseHtml(html)...) } -// Set the content of each element in the selection to specified content. The -// provided text string is escaped. +// SetText sets the content of each element in the selection to specified content. +// The provided text string is escaped. func (s *Selection) SetText(text string) *Selection { return s.SetHtml(html.EscapeString(text)) } diff --git a/vendor/github.com/PuerkitoBio/goquery/query.go b/vendor/github.com/PuerkitoBio/goquery/query.go index 1a7f873..fe86bf0 100644 --- a/vendor/github.com/PuerkitoBio/goquery/query.go +++ b/vendor/github.com/PuerkitoBio/goquery/query.go @@ -5,11 +5,7 @@ import "golang.org/x/net/html" // Is checks the current matched set of elements against a selector and // returns true if at least one of these elements matches. func (s *Selection) Is(selector string) bool { - if len(s.Nodes) > 0 { - return s.IsMatcher(compileMatcher(selector)) - } - - return false + return s.IsMatcher(compileMatcher(selector)) } // IsMatcher checks the current matched set of elements against a matcher and diff --git a/vendor/github.com/PuerkitoBio/goquery/type.go b/vendor/github.com/PuerkitoBio/goquery/type.go index e2169fa..6ad51db 100644 --- a/vendor/github.com/PuerkitoBio/goquery/type.go +++ b/vendor/github.com/PuerkitoBio/goquery/type.go @@ -31,6 +31,10 @@ func NewDocumentFromNode(root *html.Node) *Document { // NewDocument is a Document constructor that takes a string URL as argument. // It loads the specified document, parses it, and stores the root Document // node, ready to be manipulated. +// +// Deprecated: Use the net/http standard library package to make the request +// and validate the response before calling goquery.NewDocumentFromReader +// with the response's body. func NewDocument(url string) (*Document, error) { // Load the URL res, e := http.Get(url) @@ -40,10 +44,10 @@ func NewDocument(url string) (*Document, error) { return NewDocumentFromResponse(res) } -// NewDocumentFromReader returns a Document from a generic reader. +// NewDocumentFromReader returns a Document from an io.Reader. // It returns an error as second value if the reader's data cannot be parsed -// as html. It does *not* check if the reader is also an io.Closer, so the -// provided reader is never closed by this call, it is the responsibility +// as html. It does not check if the reader is also an io.Closer, the +// provided reader is never closed by this call. It is the responsibility // of the caller to close it if required. func NewDocumentFromReader(r io.Reader) (*Document, error) { root, e := html.Parse(r) @@ -56,6 +60,8 @@ func NewDocumentFromReader(r io.Reader) (*Document, error) { // NewDocumentFromResponse is another Document constructor that takes an http response as argument. // It loads the specified response's document, parses it, and stores the root Document // node, ready to be manipulated. The response's body is closed on return. +// +// Deprecated: Use goquery.NewDocumentFromReader with the response's body. func NewDocumentFromResponse(res *http.Response) (*Document, error) { if res == nil { return nil, errors.New("Response is nil") |