iLoveElysia/openbilibili
1
0
Fork 0
mirror of https://github.com/iLoveElysia/openbilibili.git synced 2026-03-14 05:46:26 -05:00
Code Issues Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Donny
2019-04-22 20:46:32 +08:00
commit 49ab8aadd1
25441 changed files with 4055000 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
vendor/github.com/jaytaylor/html2text/BUILD.bazel generated vendored Normal file
View File

@@ -0,0 +1,29 @@
load("@io_bazel_rules_go//go:def.bzl", "go_library")
go_library(
name = "go_default_library",
srcs = ["html2text.go"],
importmap = "go-common/vendor/github.com/jaytaylor/html2text",
importpath = "github.com/jaytaylor/html2text",
visibility = ["//visibility:public"],
deps = [
"//vendor/github.com/olekukonko/tablewriter:go_default_library",
"//vendor/github.com/ssor/bom:go_default_library",
"@org_golang_x_net//html:go_default_library",
"@org_golang_x_net//html/atom:go_default_library",
],
)
filegroup(
name = "package-srcs",
srcs = glob(["**"]),
tags = ["automanaged"],
visibility = ["//visibility:private"],
)
filegroup(
name = "all-srcs",
srcs = [":package-srcs"],
tags = ["automanaged"],
visibility = ["//visibility:public"],
)

22
vendor/github.com/jaytaylor/html2text/LICENSE generated vendored Normal file
View File

@@ -0,0 +1,22 @@
The MIT License (MIT)
Copyright (c) 2015 Jay Taylor
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

137
vendor/github.com/jaytaylor/html2text/README.md generated vendored Normal file
View File

@@ -0,0 +1,137 @@
# html2text
[![Documentation](https://godoc.org/github.com/jaytaylor/html2text?status.svg)](https://godoc.org/github.com/jaytaylor/html2text)
[![Build Status](https://travis-ci.org/jaytaylor/html2text.svg?branch=master)](https://travis-ci.org/jaytaylor/html2text)
[![Report Card](https://goreportcard.com/badge/github.com/jaytaylor/html2text)](https://goreportcard.com/report/github.com/jaytaylor/html2text)
### Converts HTML into text
## Introduction
Ensure your emails are readable by all!
Turns HTML into raw text, useful for sending fancy HTML emails with a equivalently nicely formatted TXT document as a fallback (e.g. for people who don't allow HTML emails or have other display issues).
html2text is a simple golang package for rendering HTML into plaintext.
There are still lots of improvements to be had, but FWIW this has worked fine for my [basic] HTML-2-text needs.
It requires go 1.x or newer ;)
## Download the package
```bash
go get github.com/jaytaylor/html2text
```
## Example usage
```go
package main
import (
"fmt"
"github.com/jaytaylor/html2text"
)
func main() {
inputHTML := `
<html>
<head>
<title>My Mega Service</title>
<link rel=\"stylesheet\" href=\"main.css\">
<style type=\"text/css\">body { color: #fff; }</style>
</head>
<body>
<div class="logo">
<a href="http://jaytaylor.com/"><img src="/logo-image.jpg" alt="Mega Service"/></a>
</div>
<h1>Welcome to your new account on my service!</h1>
<p>
Here is some more information:
<ul>
<li>Link 1: <a href="https://example.com">Example.com</a></li>
<li>Link 2: <a href="https://example2.com">Example2.com</a></li>
<li>Something else</li>
</ul>
</p>
<table>
<thead>
<tr><th>Header 1</th><th>Header 2</th></tr>
</thead>
<tfoot>
<tr><td>Footer 1</td><td>Footer 2</td></tr>
</tfoot>
<tbody>
<tr><td>Row 1 Col 1</td><td>Row 1 Col 2</td></tr>
<tr><td>Row 2 Col 1</td><td>Row 2 Col 2</td></tr>
</tbody>
</table>
</body>
</html>`
text, err := FromString(inputHTML, Options{PrettyTables: true})
if err != nil {
panic(err)
}
fmt.Println(text)
}
```
Output:
```
Mega Service ( http://jaytaylor.com/ )
******************************************
Welcome to your new account on my service!
******************************************
Here is some more information:
* Link 1: Example.com ( https://example.com )
* Link 2: Example2.com ( https://example2.com )
* Something else
+-------------+-------------+
| HEADER 1 | HEADER 2 |
+-------------+-------------+
| Row 1 Col 1 | Row 1 Col 2 |
| Row 2 Col 1 | Row 2 Col 2 |
+-------------+-------------+
| FOOTER 1 | FOOTER 2 |
+-------------+-------------+
```
## Unit-tests
Running the unit-tests is straightforward and standard:
```bash
go test
```
# License
Permissive MIT license.
## Contact
You are more than welcome to open issues and send pull requests if you find a bug or want a new feature.
If you appreciate this library please feel free to drop me a line and tell me! It's always nice to hear from people who have benefitted from my work.
Email: jay at (my github username).com
Twitter: [@jtaylor](https://twitter.com/jtaylor)

453
vendor/github.com/jaytaylor/html2text/html2text.go generated vendored Normal file
View File

@@ -0,0 +1,453 @@
package html2text
import (
"bytes"
"io"
"regexp"
"strings"
"unicode"
"github.com/olekukonko/tablewriter"
"github.com/ssor/bom"
"golang.org/x/net/html"
"golang.org/x/net/html/atom"
)
// Options provide toggles and overrides to control specific rendering behaviors.
type Options struct {
PrettyTables bool // Turns on pretty ASCII rendering for table elements.
}
// FromHTMLNode renders text output from a pre-parsed HTML document.
func FromHTMLNode(doc *html.Node, o ...Options) (string, error) {
var options Options
if len(o) > 0 {
options = o[0]
}
ctx := textifyTraverseContext{
buf: bytes.Buffer{},
options: options,
}
if err := ctx.traverse(doc); err != nil {
return "", err
}
text := strings.TrimSpace(newlineRe.ReplaceAllString(
strings.Replace(ctx.buf.String(), "\n ", "\n", -1), "\n\n"),
)
return text, nil
}
// FromReader renders text output after parsing HTML for the specified
// io.Reader.
func FromReader(reader io.Reader, options ...Options) (string, error) {
newReader, err := bom.NewReaderWithoutBom(reader)
if err != nil {
return "", err
}
doc, err := html.Parse(newReader)
if err != nil {
return "", err
}
return FromHTMLNode(doc, options...)
}
// FromString parses HTML from the input string, then renders the text form.
func FromString(input string, options ...Options) (string, error) {
bs := bom.CleanBom([]byte(input))
text, err := FromReader(bytes.NewReader(bs), options...)
if err != nil {
return "", err
}
return text, nil
}
var (
spacingRe = regexp.MustCompile(`[ \r\n\t]+`)
newlineRe = regexp.MustCompile(`\n\n+`)
)
// traverseTableCtx holds text-related context.
type textifyTraverseContext struct {
buf bytes.Buffer
prefix string
tableCtx tableTraverseContext
options Options
endsWithSpace bool
justClosedDiv bool
blockquoteLevel int
lineLength int
}
// tableTraverseContext holds table ASCII-form related context.
type tableTraverseContext struct {
header []string
body [][]string
footer []string
tmpRow int
isInFooter bool
}
func (tableCtx *tableTraverseContext) init() {
tableCtx.body = [][]string{}
tableCtx.header = []string{}
tableCtx.footer = []string{}
tableCtx.isInFooter = false
tableCtx.tmpRow = 0
}
func (ctx *textifyTraverseContext) handleElement(node *html.Node) error {
ctx.justClosedDiv = false
switch node.DataAtom {
case atom.Br:
return ctx.emit("\n")
case atom.H1, atom.H2, atom.H3:
subCtx := textifyTraverseContext{}
if err := subCtx.traverseChildren(node); err != nil {
return err
}
str := subCtx.buf.String()
dividerLen := 0
for _, line := range strings.Split(str, "\n") {
if lineLen := len([]rune(line)); lineLen-1 > dividerLen {
dividerLen = lineLen - 1
}
}
var divider string
if node.DataAtom == atom.H1 {
divider = strings.Repeat("*", dividerLen)
} else {
divider = strings.Repeat("-", dividerLen)
}
if node.DataAtom == atom.H3 {
return ctx.emit("\n\n" + str + "\n" + divider + "\n\n")
}
return ctx.emit("\n\n" + divider + "\n" + str + "\n" + divider + "\n\n")
case atom.Blockquote:
ctx.blockquoteLevel++
ctx.prefix = strings.Repeat(">", ctx.blockquoteLevel) + " "
if err := ctx.emit("\n"); err != nil {
return err
}
if ctx.blockquoteLevel == 1 {
if err := ctx.emit("\n"); err != nil {
return err
}
}
if err := ctx.traverseChildren(node); err != nil {
return err
}
ctx.blockquoteLevel--
ctx.prefix = strings.Repeat(">", ctx.blockquoteLevel)
if ctx.blockquoteLevel > 0 {
ctx.prefix += " "
}
return ctx.emit("\n\n")
case atom.Div:
if ctx.lineLength > 0 {
if err := ctx.emit("\n"); err != nil {
return err
}
}
if err := ctx.traverseChildren(node); err != nil {
return err
}
var err error
if !ctx.justClosedDiv {
err = ctx.emit("\n")
}
ctx.justClosedDiv = true
return err
case atom.Li:
if err := ctx.emit("* "); err != nil {
return err
}
if err := ctx.traverseChildren(node); err != nil {
return err
}
return ctx.emit("\n")
case atom.B, atom.Strong:
subCtx := textifyTraverseContext{}
subCtx.endsWithSpace = true
if err := subCtx.traverseChildren(node); err != nil {
return err
}
str := subCtx.buf.String()
return ctx.emit("*" + str + "*")
case atom.A:
// If image is the only child, take its alt text as the link text.
if img := node.FirstChild; img != nil && node.LastChild == img && img.DataAtom == atom.Img {
if altText := getAttrVal(img, "alt"); altText != "" {
if err := ctx.emit(altText); err != nil {
return err
}
}
} else if err := ctx.traverseChildren(node); err != nil {
return err
}
hrefLink := ""
if attrVal := getAttrVal(node, "href"); attrVal != "" {
attrVal = ctx.normalizeHrefLink(attrVal)
if attrVal != "" {
hrefLink = "( " + attrVal + " )"
}
}
return ctx.emit(hrefLink)
case atom.P, atom.Ul:
return ctx.paragraphHandler(node)
case atom.Table, atom.Tfoot, atom.Th, atom.Tr, atom.Td:
if ctx.options.PrettyTables {
return ctx.handleTableElement(node)
} else if node.DataAtom == atom.Table {
return ctx.paragraphHandler(node)
}
return ctx.traverseChildren(node)
case atom.Style, atom.Script, atom.Head:
// Ignore the subtree.
return nil
default:
return ctx.traverseChildren(node)
}
}
// paragraphHandler renders node children surrounded by double newlines.
func (ctx *textifyTraverseContext) paragraphHandler(node *html.Node) error {
if err := ctx.emit("\n\n"); err != nil {
return err
}
if err := ctx.traverseChildren(node); err != nil {
return err
}
return ctx.emit("\n\n")
}
// handleTableElement is only to be invoked when options.PrettyTables is active.
func (ctx *textifyTraverseContext) handleTableElement(node *html.Node) error {
if !ctx.options.PrettyTables {
panic("handleTableElement invoked when PrettyTables not active")
}
switch node.DataAtom {
case atom.Table:
if err := ctx.emit("\n\n"); err != nil {
return err
}
// Re-intialize all table context.
ctx.tableCtx.init()
// Browse children, enriching context with table data.
if err := ctx.traverseChildren(node); err != nil {
return err
}
buf := &bytes.Buffer{}
table := tablewriter.NewWriter(buf)
table.SetHeader(ctx.tableCtx.header)
table.SetFooter(ctx.tableCtx.footer)
table.AppendBulk(ctx.tableCtx.body)
// Render the table using ASCII.
table.Render()
if err := ctx.emit(buf.String()); err != nil {
return err
}
return ctx.emit("\n\n")
case atom.Tfoot:
ctx.tableCtx.isInFooter = true
if err := ctx.traverseChildren(node); err != nil {
return err
}
ctx.tableCtx.isInFooter = false
case atom.Tr:
ctx.tableCtx.body = append(ctx.tableCtx.body, []string{})
if err := ctx.traverseChildren(node); err != nil {
return err
}
ctx.tableCtx.tmpRow++
case atom.Th:
res, err := ctx.renderEachChild(node)
if err != nil {
return err
}
ctx.tableCtx.header = append(ctx.tableCtx.header, res)
case atom.Td:
res, err := ctx.renderEachChild(node)
if err != nil {
return err
}
if ctx.tableCtx.isInFooter {
ctx.tableCtx.footer = append(ctx.tableCtx.footer, res)
} else {
ctx.tableCtx.body[ctx.tableCtx.tmpRow] = append(ctx.tableCtx.body[ctx.tableCtx.tmpRow], res)
}
}
return nil
}
func (ctx *textifyTraverseContext) traverse(node *html.Node) error {
switch node.Type {
default:
return ctx.traverseChildren(node)
case html.TextNode:
data := strings.Trim(spacingRe.ReplaceAllString(node.Data, " "), " ")
return ctx.emit(data)
case html.ElementNode:
return ctx.handleElement(node)
}
}
func (ctx *textifyTraverseContext) traverseChildren(node *html.Node) error {
for c := node.FirstChild; c != nil; c = c.NextSibling {
if err := ctx.traverse(c); err != nil {
return err
}
}
return nil
}
func (ctx *textifyTraverseContext) emit(data string) error {
if data == "" {
return nil
}
var (
lines = ctx.breakLongLines(data)
err error
)
for _, line := range lines {
runes := []rune(line)
startsWithSpace := unicode.IsSpace(runes[0])
if !startsWithSpace && !ctx.endsWithSpace {
if err = ctx.buf.WriteByte(' '); err != nil {
return err
}
ctx.lineLength++
}
ctx.endsWithSpace = unicode.IsSpace(runes[len(runes)-1])
for _, c := range line {
if _, err = ctx.buf.WriteString(string(c)); err != nil {
return err
}
ctx.lineLength++
if c == '\n' {
ctx.lineLength = 0
if ctx.prefix != "" {
if _, err = ctx.buf.WriteString(ctx.prefix); err != nil {
return err
}
}
}
}
}
return nil
}
const maxLineLen = 74
func (ctx *textifyTraverseContext) breakLongLines(data string) []string {
// Only break lines when in blockquotes.
if ctx.blockquoteLevel == 0 {
return []string{data}
}
var (
ret = []string{}
runes = []rune(data)
l = len(runes)
existing = ctx.lineLength
)
if existing >= maxLineLen {
ret = append(ret, "\n")
existing = 0
}
for l+existing > maxLineLen {
i := maxLineLen - existing
for i >= 0 && !unicode.IsSpace(runes[i]) {
i--
}
if i == -1 {
// No spaces, so go the other way.
i = maxLineLen - existing
for i < l && !unicode.IsSpace(runes[i]) {
i++
}
}
ret = append(ret, string(runes[:i])+"\n")
for i < l && unicode.IsSpace(runes[i]) {
i++
}
runes = runes[i:]
l = len(runes)
existing = 0
}
if len(runes) > 0 {
ret = append(ret, string(runes))
}
return ret
}
func (ctx *textifyTraverseContext) normalizeHrefLink(link string) string {
link = strings.TrimSpace(link)
link = strings.TrimPrefix(link, "mailto:")
return link
}
// renderEachChild visits each direct child of a node and collects the sequence of
// textuual representaitons separated by a single newline.
func (ctx *textifyTraverseContext) renderEachChild(node *html.Node) (string, error) {
buf := &bytes.Buffer{}
for c := node.FirstChild; c != nil; c = c.NextSibling {
s, err := FromHTMLNode(c, ctx.options)
if err != nil {
return "", err
}
if _, err = buf.WriteString(s); err != nil {
return "", err
}
if c.NextSibling != nil {
if err = buf.WriteByte('\n'); err != nil {
return "", err
}
}
}
return buf.String(), nil
}
func getAttrVal(node *html.Node, attrName string) string {
for _, attr := range node.Attr {
if attr.Key == attrName {
return attr.Val
}
}
return ""
}