python网络爬虫爬取整个网页

AUTHORS.txt LICENSE.txt MANIFEST.in NEWS.rst README.rst pyproject.toml setup.cfg setup.py docs/Makefile docs/__init__.py docs/conf.py docs/configuration.rst docs/cookbook.rst docs/development.rst docs/docutils.conf docs/index.rst docs/installing.rst docs/logic.rst docs/make.bat docs/news.rst docs/pipext.py docs/quickstart.rst docs/usage.rst docs/user_guide.rst docs/man/pip.rst docs/man/commands/check.rst docs/man/commands/config.rst docs/man/commands/download.rst docs/man/commands/freeze.rst docs/man/commands/hash.rst docs/man/commands/help.rst docs/man/commands/install.rst docs/man/commands/list.rst docs/man/commands/search.rst docs/man/commands/show.rst docs/man/commands/uninstall.rst docs/man/commands/wheel.rst docs/reference/index.rst docs/reference/pip.rst docs/reference/pip_check.rst docs/reference/pip_config.rst docs/reference/pip_download.rst docs/reference/pip_freeze.rst docs/reference/pip_hash.rst docs/reference/pip_install.rst docs/reference/pip_list.rst docs/reference/pip_search.rst docs/reference/pip_show.rst docs/reference/pip_uninstall.rst docs/reference/pip_wheel.rst src/pip/__init__.py src/pip/__main__.py src/pip.egg-info/PKG-INFO src/pip.egg-info/SOURCES.txt src/pip.egg-info/dependency_links.txt src/pip.egg-info/entry_points.txt src/pip.egg-info/not-zip-safe src/pip.egg-info/requires.txt src/pip.egg-info/top_level.txt src/pip/_internal/__init__.py src/pip/_internal/basecommand.py src/pip/_internal/baseparser.py src/pip/_internal/build_env.py src/pip/_internal/cache.py src/pip/_internal/cmdoptions.py src/pip/_internal/compat.py src/pip/_internal/configuration.py src/pip/_internal/download.py src/pip/_internal/exceptions.py src/pip/_internal/index.py src/pip/_internal/locations.py src/pip/_internal/pep425tags.py src/pip/_internal/resolve.py src/pip/_internal/status_codes.py src/pip/_internal/wheel.py src/pip/_internal/commands/__init__.py src/pip/_internal/commands/check.py src/pip/_internal/commands/completion.py src/pip/_internal/commands/configuration.py src/pip/_internal/commands/download.py src/pip/_internal/commands/freeze.py src/pip/_internal/commands/hash.py src/pip/_internal/commands/help.py src/pip/_internal/commands/install.py src/pip/_internal/commands/list.py src/pip/_internal/commands/search.py src/pip/_internal/commands/show.py src/pip/_internal/commands/uninstall.py src/pip/_internal/commands/wheel.py src/pip/_internal/models/__init__.py src/pip/_internal/models/index.py src/pip/_internal/operations/__init__.py src/pip/_internal/operations/check.py src/pip/_internal/operations/freeze.py src/pip/_internal/operations/prepare.py src/pip/_internal/req/__init__.py src/pip/_internal/req/req_file.py src/pip/_internal/req/req_install.py src/pip/_internal/req/req_set.py src/pip/_internal/req/req_uninstall.py src/pip/_internal/utils/__init__.py src/pip/_internal/utils/appdirs.py src/pip/_internal/utils/deprecation.py src/pip/_internal/utils/encoding.py src/pip/_internal/utils/filesystem.py src/pip/_internal/utils/glibc.py src/pip/_internal/utils/hashes.py src/pip/_internal/utils/logging.py src/pip/_internal/utils/misc.py src/pip/_internal/utils/outdated.py src/pip/_internal/utils/packaging.py src/pip/_internal/utils/setuptools_build.py src/pip/_internal/utils/temp_dir.py src/pip/_internal/utils/typing.py src/pip/_internal/utils/ui.py src/pip/_internal/vcs/__init__.py src/pip/_internal/vcs/bazaar.py src/pip/_internal/vcs/git.py src/pip/_internal/vcs/mercurial.py src/pip/_internal/vcs/subversion.py src/pip/_vendor/README.rst src/pip/_vendor/__init__.py src/pip/_vendor/appdirs.py src/pip/_vendor/distro.py src/pip/_vendor/ipaddress.py src/pip/_vendor/pyparsing.py src/pip/_vendor/retrying.py src/pip/_vendor/six.py src/pip/_vendor/vendor.txt src/pip/_vendor/cachecontrol/__init__.py src/pip/_vendor/cachecontrol/_cmd.py src/pip/_vendor/cachecontrol/adapter.py src/pip/_vendor/cachecontrol/cache.py src/pip/_vendor/cachecontrol/compat.py src/pip/_vendor/cachecontrol/controller.py src/pip/_vendor/cachecontrol/filewrapper.py src/pip/_vendor/cachecontrol/heuristics.py src/pip/_vendor/cachecontrol/serialize.py src/pip/_vendor/cachecontrol/wrapper.py src/pip/_vendor/cachecontrol/caches/__init__.py src/pip/_vendor/cachecontrol/caches/file_cache.py src/pip/_vendor/cachecontrol/caches/redis_cache.py src/pip/_vendor/certifi/__init__.py src/pip/_vendor/certifi/__main__.py src/pip/_vendor/certifi/cacert.pem src/pip/_vendor/certifi/core.py src/pip/_vendor/chardet/__init__.py src/pip/_vendor/chardet/big5freq.py src/pip/_vendor/chardet/big5prober.py src/pip/_vendor/chardet/chardistribution.py src/pip/_vendor/chardet/charsetgroupprober.py src/pip/_vendor/chardet/charsetprober.py src/pip/_vendor/chardet/codingstatemachine.py src/pip/_vendor/chardet/compat.py src/pip/_vendor/chardet/cp949prober.py src/pip/_vendor/chardet/enums.py src/pip/_vendor/chardet/escprober.py src/pip/_vendor/chardet/escsm.py src/pip/_vendor/chardet/eucjpprober.py src/pip/_vendor/chardet/euckrfreq.py src/pip/_vendor/chardet/euckrprober.py src/pip/_vendor/chardet/euctwfreq.py src/pip/_vendor/chardet/euctwprober.py src/pip/_vendor/chardet/gb2312freq.py src/pip/_vendor/chardet/gb2312prober.py src/pip/_vendor/chardet/hebrewprober.py src/pip/_vendor/chardet/jisfreq.py src/pip/_vendor/chardet/jpcntx.py src/pip/_vendor/chardet/langbulgarianmodel.py src/pip/_vendor/chardet/langcyrillicmodel.py src/pip/_vendor/chardet/langgreekmodel.py src/pip/_vendor/chardet/langhebrewmodel.py src/pip/_vendor/chardet/langhungarianmodel.py src/pip/_vendor/chardet/langthaimodel.py src/pip/_vendor/chardet/langturkishmodel.py src/pip/_vendor/chardet/latin1prober.py src/pip/_vendor/chardet/mbcharsetprober.py src/pip/_vendor/chardet/mbcsgroupprober.py src/pip/_vendor/chardet/mbcssm.py src/pip/_vendor/chardet/sbcharsetprober.py src/pip/_vendor/chardet/sbcsgroupprober.py src/pip/_vendor/chardet/sjisprober.py src/pip/_vendor/chardet/universaldetector.py src/pip/_vendor/chardet/utf8prober.py src/pip/_vendor/chardet/version.py src/pip/_vendor/chardet/cli/__init__.py src/pip/_vendor/chardet/cli/chardetect.py src/pip/_vendor/colorama/__init__.py src/pip/_vendor/colorama/ansi.py src/pip/_vendor/colorama/ansitowin32.py src/pip/_vendor/colorama/initialise.py src/pip/_vendor/colorama/win32.py src/pip/_vendor/colorama/winterm.py src/pip/_vendor/distlib/__init__.py src/pip/_vendor/distlib/compat.py src/pip/_vendor/distlib/database.py src/pip/_vendor/distlib/index.py src/pip/_vendor/distlib/locators.py src/pip/_vendor/distlib/manifest.py src/pip/_vendor/distlib/markers.py src/pip/_vendor/distlib/metadata.py src/pip/_vendor/distlib/resources.py src/pip/_vendor/distlib/scripts.py src/pip/_vendor/distlib/t32.exe src/pip/_vendor/distlib/t64.exe src/pip/_vendor/distlib/util.py src/pip/_vendor/distlib/version.py src/pip/_vendor/distlib/w32.exe src/pip/_vendor/distlib/w64.exe src/pip/_vendor/distlib/wheel.py src/pip/_vendor/distlib/_backport/__init__.py src/pip/_vendor/distlib/_backport/misc.py src/pip/_vendor/distlib/_backport/shutil.py src/pip/_vendor/distlib/_backport/sysconfig.cfg src/pip/_vendor/distlib/_backport/sysconfig.py src/pip/_vendor/distlib/_backport/tarfile.py src/pip/_vendor/html5lib/__init__.py src/pip/_vendor/html5lib/_ihatexml.py src/pip/_vendor/html5lib/_inputstream.py src/pip/_vendor/html5lib/_tokenizer.py src/pip/_vendor/html5lib/_utils.py src/pip/_vendor/html5lib/constants.py src/pip/_vendor/html5lib/html5parser.py src/pip/_vendor/html5lib/serializer.py src/pip/_vendor/html5lib/_trie/__init__.py src/pip/_vendor/html5lib/_trie/_base.py src/pip/_vendor/html5lib/_trie/datrie.py src/pip/_vendor/html5lib/_trie/py.py src/pip/_vendor/html5lib/filters/__init__.py src/pip/_vendor/html5lib/filters/alphabeticalattributes.py src/pip/_vendor/html5lib/filters/base.py src/pip/_vendor/html5lib/filters/inject_meta_charset.py src/pip/_vendor/html5lib/filters/lint.py src/pip/_vendor/html5lib/filters/optionaltags.py src/pip/_vendor/html5lib/filters/sanitizer.py src/pip/_vendor/html5lib/filters/whitespace.py src/pip/_vendor/html5li