kwaziidev / textractor Goto Github PK
View Code? Open in Web Editor NEW从html中提取正文,用于新闻类网页
License: MIT License
从html中提取正文,用于新闻类网页
License: MIT License
fatal output:
runtime: goroutine stack exceeds 1000000000-byte limit
runtime: sp=0xc022a823a8 stack=[0xc022a82000, 0xc042a82000]
fatal error: stack overflow
runtime stack:
runtime.throw(0x1132e81, 0xe)
/usr/local/go/src/runtime/panic.go:1117 +0x72
runtime.newstack()
/usr/local/go/src/runtime/stack.go:1069 +0x7ed
runtime.morestack()
/usr/local/go/src/runtime/asm_amd64.s:458 +0x8f
goroutine 1031 [running]:
runtime.concatstrings(0x0, 0xc022a82400, 0x2, 0x2, 0x0, 0x0)
/usr/local/go/src/runtime/string.go:24 +0x2f4 fp=0xc022a823b8 sp=0xc022a823b0 pc=0x453c14
runtime.concatstring2(0x0, 0x0, 0x0, 0x112f107, 0x2, 0xc022a82460, 0x2)
/usr/local/go/src/runtime/string.go:59 +0x47 fp=0xc022a823f8 sp=0xc022a823b8 pc=0x453c67
github.com/andybalholm/cascadia.(*parser).parseName(0xc022a827d8, 0x0, 0x0, 0x112f110, 0x2)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/parser.go:134 +0xc5 fp=0xc022a82458 sp=0xc022a823f8 pc=0x714805
github.com/andybalholm/cascadia.(*parser).parseIdentifier(0xc022a827d8, 0x10, 0x7fc249a3ef18, 0x10, 0xc014e7d2f0)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/parser.go:114 +0x97 fp=0xc022a824c8 sp=0xc022a82458 pc=0x714577
github.com/andybalholm/cascadia.(*parser).parseTypeSelector(0xc022a827d8, 0x0, 0xc014e7d2f0, 0x0, 0x1)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/parser.go:306 +0x2f fp=0xc022a82520 sp=0xc022a824c8 pc=0x7152af
github.com/andybalholm/cascadia.(*parser).parseSimpleSelectorSequence(0xc022a827d8, 0x203000, 0xc022a82728, 0x7fc21f5bb280, 0x40)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/parser.go:720 +0x718 fp=0xc022a82690 sp=0xc022a82520 pc=0x718d58
github.com/andybalholm/cascadia.(*parser).parseSelector(0xc022a827d8, 0x0, 0xc014e6dc00, 0x1298070, 0xc014e7d2e0)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/parser.go:779 +0x3d fp=0xc022a82708 sp=0xc022a82690 pc=0x718f1d
github.com/andybalholm/cascadia.(*parser).parseSelectorGroup(0xc022a827d8, 0x0, 0x8, 0x8, 0xc022a82828, 0x203005)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/parser.go:820 +0x2f fp=0xc022a82780 sp=0xc022a82708 pc=0x7191af
github.com/andybalholm/cascadia.ParseGroup(0x112f107, 0xb, 0xc014e84600, 0x30, 0x28, 0x103afe0, 0x0)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/selector.go:67 +0x72 fp=0xc022a82808 sp=0xc022a82780 pc=0x719472
github.com/andybalholm/cascadia.Compile(...)
/opt/gopath/pkg/mod/github.com/andybalholm/[email protected]/selector.go:10github.com/PuerkitoBio/goquery.compileMatcher(0x112f107, 0xb, 0xc022a828c0, 0xc0005ee800)
/opt/gopath/pkg/mod/github.com/!puerkito!bio/[email protected]/type.go:167 +0x39 fp=0xc022a82868 sp=0xc022a82808 pc=0x72d8b9
github.com/PuerkitoBio/goquery.(*Selection).Find(0xc014e84600, 0x112f107, 0xb, 0x0)
/opt/gopath/pkg/mod/github.com/!puerkito!bio/[email protected]/traversal.go:24 +0x39 fp=0xc022a828d0 sp=0xc022a82868 pc=0x728b59
github.com/gloomyzerg/textractor.findHtag(0xc014e845a0, 0x112f107, 0xb, 0xc014e845d0)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:37 +0xe5 fp=0xc022a82930 sp=0xc022a828d0 pc=0xea7c45
github.com/gloomyzerg/textractor.findHtag(0xc014e84540, 0x112f107, 0xb, 0xc014e84570)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a82990 sp=0xc022a82930 pc=0xea7ca5
github.com/gloomyzerg/textractor.findHtag(0xc014e844e0, 0x112f107, 0xb, 0xc014e84510)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a829f0 sp=0xc022a82990 pc=0xea7ca5
github.com/gloomyzerg/textractor.findHtag(0xc014e84480, 0x112f107, 0xb, 0xc014e844b0)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a82a50 sp=0xc022a829f0 pc=0xea7ca5
github.com/gloomyzerg/textractor.findHtag(0xc014e84420, 0x112f107, 0xb, 0xc014e84450)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a82ab0 sp=0xc022a82a50 pc=0xea7ca5
github.com/gloomyzerg/textractor.findHtag(0xc014e843c0, 0x112f107, 0xb, 0xc014e843f0)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a82b10 sp=0xc022a82ab0 pc=0xea7ca5
github.com/gloomyzerg/textractor.findHtag(0xc014e84360, 0x112f107, 0xb, 0xc014e84390)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a82b70 sp=0xc022a82b10 pc=0xea7ca5
github.com/gloomyzerg/textractor.findHtag(0xc014e84300, 0x112f107, 0xb, 0xc014e84330)
/opt/gopath/pkg/mod/github.com/gloomyzerg/[email protected]/title.go:41 +0x145 fp=0xc022a82bd0 sp=0xc022a82b70 pc=0xea7ca5
...
...
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.