google的html解析器 gumbo-parser-master

  google的html解析器 C语言解析html网页文件(gumbo-parser-master )

gumbo-parser-master
...................\.clang-format,1969,2015-12-04
...................\.gitignore,878,2015-12-04
...................\.gitmodules,214,2015-12-04
...................\.travis.yml,640,2015-12-04
...................\appveyor.yml,82,2015-12-04
...................\autogen.sh,1206,2015-12-04
...................\benchmarks
...................\..........\arabic_newspapers.html,79355,2015-12-04
...................\..........\baidu.html,76984,2015-12-04
...................\..........\bbc.html,117580,2015-12-04
...................\..........\benchmark.cc,2254,2015-12-04
...................\..........\google.html,344037,2015-12-04
...................\..........\hacker_news.html,29802,2015-12-04
...................\..........\html5_spec.html,7974278,2015-12-04
...................\..........\wikipedia.html,522902,2015-12-04
...................\..........\xinhua.html,329791,2015-12-04
...................\..........\yahoo.html,439449,2015-12-04
...................\CHANGES.md,2615,2015-12-04
...................\configure.ac,929,2015-12-04
...................\CONTRIBUTING.md,3644,2015-12-04
...................\htm" target=_blank>COPYING,11357,2015-12-04
...................\DEBUGGING.md,3553,2015-12-04
...................\htm" target=_blank>Doxyfile,75546,2015-12-04
...................\examples
...................\........\clean_text.cc,2135,2015-12-04
...................\........\find_links.cc,1936,2015-12-04
...................\........\get_title.c,2839,2015-12-04
...................\........\positions_of_class.cc,3117,2015-12-04
...................\........\prettyprint.cc,10596,2015-12-04
...................\........\serialize.cc,8839,2015-12-04
...................\genperf.py,861,2015-12-04
...................\gentags.py,971,2015-12-04
...................\gtest.gyp,4551,2015-12-04
...................\gumbo.pc.in,238,2015-12-04
...................\gumbo_parser.gyp,2023,2015-12-04
...................\Makefile.am,3875,2015-12-04
...................\python
...................\......\gumbo
...................\......\.....\gumboc.py,11842,2015-12-04
...................\......\.....\gumboc_tags.py,1715,2015-12-04
...................\......\.....\gumboc_test.py,4821,2015-12-04
...................\......\.....\html5lib_adapter.py,5095,2015-12-04
...................\......\.....\html5lib_adapter_test.py,6251,2015-12-04
...................\......\.....\soup_adapter.py,3577,2015-12-04
...................\......\.....\soup_adapter_test.py,2128,2015-12-04
...................\......\.....\__init__.py,1284,2015-12-04
...................\README.md,8518,2015-12-04
...................\setup.py,6604,2015-12-04
...................\src
...................\...\attribute.c,1374,2015-12-04
...................\...\attribute.h,1045,2015-12-04
...................\...\char_ref.c,749143,2015-12-04
...................\...\char_ref.h,2214,2015-12-04
...................\...\char_ref.rl,128173,2015-12-04
...................\...\error.c,10544,2015-12-04
...................\...\error.h,7935,2015-12-04
...................\...\gumbo.h,23760,2015-12-04
...................\...\insertion_mode.h,1897,2015-12-04
...................\...\parser.c,176362,2015-12-04
...................\...\parser.h,2049,2015-12-04
...................\...\string_buffer.c,3731,2015-12-04
...................\...\string_buffer.h,3063,2015-12-04
...................\...\string_piece.c,1562,2015-12-04
...................\...\string_piece.h,1210,2015-12-04
...................\...\tag.c,2669,2015-12-04
...................\...\tag.in,850,2015-12-04
...................\...\tag_enum.h,2603,2015-12-04
...................\...\tag_gperf.h,6907,2015-12-04
...................\...\tag_sizes.h,558,2015-12-04
...................\...\tag_strings.h,1403,2015-12-04
...................\...\tokenizer.c,117891,2015-12-04
...................\...\tokenizer.h,4621,2015-12-04
...................\...\tokenizer_states.h,3737,2015-12-04
...................\...\token_type.h,1109,2015-12-04
...................\...\utf8.c,10411,2015-12-04
...................\...\utf8.h,5004,2015-12-04
...................\...\util.c,1782,2015-12-04
...................\...\util.h,2029,2015-12-04
...................\...\vector.c,3734,2015-12-04
...................\...\vector.h,2398,2015-12-04
...................\testdata
...................\tests
...................\.....\attribute.cc,1396,2015-12-04
...................\.....\char_ref.cc,5204,2015-12-04
...................\.....\parser.cc,65222,2015-12-04
...................\.....\string_buffer.cc,3158,2015-12-04
...................\.....\string_piece.cc,2542,2015-12-04
...................\.....\test_utils.cc,7608,2015-12-04
...................\.....\test_utils.h,2608,2015-12-04
...................\.....\tokenizer.cc,23069,2015-12-04
...................\.....\utf8.cc,17049,2015-12-04
...................\.....\vector.cc,4711,2015-12-04
...................\htm" target=_blank>THANKS,595,2015-12-04
...................\third_party
...................\...........\gtest
...................\visualc
...................\.......\gumbo.vcxproj,4933,2015-12-04
...................\.......\gumbo.vcxproj.filters,3398,2015-12-04
...................\.......\gumbo.vcxproj.user,162,2015-12-04