{"id":1673,"date":"2018-06-22T07:59:47","date_gmt":"2018-06-21T23:59:47","guid":{"rendered":"http:\/\/www.yueguangzu.net\/?p=1673"},"modified":"2018-06-22T07:59:47","modified_gmt":"2018-06-21T23:59:47","slug":"beautifulsoup","status":"publish","type":"post","link":"http:\/\/www.yueguangzu.net\/?p=1673","title":{"rendered":"beautifulsoup"},"content":{"rendered":"

 <\/p>\n

\n
\n
\n
\n
\n
\n
\n
\n\n\n\n\n\n\n\n\n
\u89e3\u6790\u5668<\/th>\n\u4f7f\u7528\u65b9\u6cd5<\/th>\n\u4f18\u52bf<\/th>\n\u52a3\u52bf<\/th>\n<\/tr>\n<\/thead>\n
Python\u6807\u51c6\u5e93<\/td>\nBeautifulSoup(markup, “html.parser”)<\/td>\nPython\u7684\u5185\u7f6e\u6807\u51c6\u5e93\u3001\u6267\u884c\u901f\u5ea6\u9002\u4e2d \u3001\u6587\u6863\u5bb9\u9519\u80fd\u529b\u5f3a<\/td>\nPython 2.7.3 or 3.2.2)\u524d\u7684\u7248\u672c\u4e2d\u6587\u5bb9\u9519\u80fd\u529b\u5dee<\/td>\n<\/tr>\n
lxml HTML \u89e3\u6790\u5668<\/td>\nBeautifulSoup(markup, “lxml”)<\/td>\n\u901f\u5ea6\u5feb\u3001\u6587\u6863\u5bb9\u9519\u80fd\u529b\u5f3a<\/td>\n\u9700\u8981\u5b89\u88c5C\u8bed\u8a00\u5e93<\/td>\n<\/tr>\n
lxml XML \u89e3\u6790\u5668<\/td>\nBeautifulSoup(markup, “xml”)<\/td>\n\u901f\u5ea6\u5feb\u3001\u552f\u4e00\u652f\u6301XML\u7684\u89e3\u6790\u5668<\/td>\n\u9700\u8981\u5b89\u88c5C\u8bed\u8a00\u5e93<\/td>\n<\/tr>\n
html5lib<\/td>\nBeautifulSoup(markup, “html5lib”)<\/td>\n\u6700\u597d\u7684\u5bb9\u9519\u6027\u3001\u4ee5\u6d4f\u89c8\u5668\u7684\u65b9\u5f0f\u89e3\u6790\u6587\u6863\u3001\u751f\u6210HTML5\u683c\u5f0f\u7684\u6587\u6863<\/td>\n\u901f\u5ea6\u6162\u3001\u4e0d\u4f9d\u8d56\u5916\u90e8\u6269\u5c55<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n

 <\/p>\n

\u57fa\u672c\u7528\u6cd5<\/span><\/span>from bs4 import BeautifulSoup<\/span><\/p>\n

html=’<div class=”ff”><\/span>6666<\/div><\/span>‘<\/span><\/span><\/p>\n

soup=BeautifulSoup(”)<\/span><\/p>\n

\u9009\u62e9\u5143\u7d20<\/span><\/span>soup.div –\u83b7\u53d6\u8282\u70b9\u6807\u7b7e,\u8f93\u51fa\u4e3a’<div class=”ff”><\/span>6666<\/div><\/span>‘<\/span>soup.div.string<\/span><\/p>\n

–\u83b7\u53d6\u6807\u7b7e\u6587\u672c \u8f93\u51fa 6666<\/span><\/p>\n

soup.prettify() –\u6807\u51c6\u5316 \u81ea\u52a8\u8865\u5168html\u6587\u6863\u524d\u540e\u6807\u7b7e <\/span><\/p>\n

\u8f93\u51fa<\/span><\/p>\n

‘<html><\/span>\\n <body><\/span>\\n <div class=”ff”><\/span>\\n 6665\\n <\/div><\/span>\\n <\/body><\/span>\\n<\/html><\/span>‘<\/span><\/p>\n

\u9009\u62e9\u540d\u79f0<\/span><\/p>\n

soup.div.name >> div<\/span><\/p>\n

\u9009\u62e9\u5c5e\u6027<\/span><\/p>\n

soup.div.attrs[‘class’]<\/span><\/p>\n

soup.div[‘class’]<\/span><\/p>\n

–\u5747\u8f93\u51fa\u5217\u8868 [‘ff’]<\/span><\/p>\n

\u9009\u62e9\u5185\u5bb9<\/span>soup.div.string<\/span><\/p>\n

–\u53ea\u8fd4\u56de\u7b2c\u4e00\u4e2a<\/span>html=’<div class=”ff”><\/span><span><\/span>6666<\/span><\/span><\/div><\/span>‘<\/span>soup.div.span.string<\/span><\/p>\n

\u5b50\u8282\u70b9<\/span><\/p>\n

soup.p.contents >>\u51fa\u6765\u4e00\u4e2a\u5217\u8868,\u5305\u542b\u7a7a\u683c<\/span><\/p>\n

soup.p.children >>\u51fa\u6765\u4e00\u4e2a\u8fed\u4ee3\u5668<\/span><\/p>\n

soup.p.descendants >>\u51fa\u6765\u4e00\u4e2a\u751f\u6210\u5668<\/span><\/p>\n

soup.a.parent –\u5f53\u524d\u5143\u7d20\u7684\u7236\u8282\u70b9<\/span><\/p>\n

soup.a.parents –\u5f53\u524d\u5143\u7d20\u7684\u6240\u4ee5\u7236\u8282\u70b9<\/span><\/p>\n

list(soup.a.next_siblings) –\u6240\u6709\u5144\u5f1f\u8282\u70b9 (\u751f\u6210\u5668)<\/span>\u6807\u51c6\u9009\u62e9\u5668<\/span><\/p>\n

soup.find(‘ul’) >>\u67e5\u627e\u7b2c\u4e00\u4e2aul\u8282\u70b9\u5e76\u8fd4\u56de\u6807\u7b7e\u5185\u5bb9<\/span><\/p>\n

<ul class=”list” id=”list-1″><\/span>\\n<li class=”element”><\/span>Foo<\/li><\/span>\\n<li class=”element”><\/span>Bar<\/li><\/span>\\n<li class=”element”><\/span>Jay<\/li><\/span>\\n<\/ul><\/span><\/span><\/p>\n

soup.find_all(‘ul’) –\u67e5\u627e\u6240\u6709ul\u6807\u7b7e\u5e76\u8fd4\u56de\u5217\u8868<\/span><\/p>\n

[<ul class=”list” id=”list-1″><\/span>\\n<li class=”element”><\/span>Foo<\/li><\/span>\\n<li class=”element”><\/span>Bar<\/li><\/span>\\n<li class=”element”><\/span>Jay<\/li><\/span>\\n<\/ul><\/span>,<\/span> <ul class=”list list-small” id=”list-2″><\/span>\\n<li class=”element”><\/span>Foo<\/li><\/span>\\n<li class=”element”><\/span>Bar<\/li><\/span>\\n<\/ul><\/span>]<\/span><\/p>\n

attrs<\/span><\/p>\n

soup.find_all(attrs={‘name’: ‘elements’}) –attrs\u5c5e\u6027\u9009\u62e9\u5668,\u5185\u63a5\u4e00\u4e2a\u5bf9\u8c61<\/span><\/p>\n

[<ul class=”list” id=”list-1″ name=”elements”><\/span>\\n<li class=”element”><\/span>Foo<\/li><\/span>\\n<li class=”element”><\/span>Bar<\/li><\/span>\\n<li class=”element”><\/span>Jay<\/li><\/span>\\n<\/ul><\/span>]<\/span><\/p>\n

\u76f4\u63a5class,id\u9009\u62e9\u5668<\/span><\/p>\n

soup.find_all(class=”list list-small”) –class\u662f\u5173\u952e\u5b57<\/em><\/span><\/span><\/p>\n

text<\/span><\/p>\n

soup.find_all(text=”Bar”) >> [u’Bar’, u’Bar’]<\/span><\/p>\n

find<\/span><\/p>\n

find_parents()<\/span><\/p>\n

find_parent()<\/span><\/p>\n

find_parents()<\/span>\u8fd4\u56de\u6240\u6709\u7956\u5148\u8282\u70b9\uff0cfind_parent()\u8fd4\u56de\u76f4\u63a5\u7236\u8282\u70b9\u3002<\/span><\/p>\n

find_next_siblings() find_next_sibling()<\/h3>\n

find_next_siblings() find_next_sibling()<\/span>find_next_siblings()\u8fd4\u56de\u540e\u9762\u6240\u6709\u5144\u5f1f\u8282\u70b9\uff0cfind_next_sibling()\u8fd4\u56de\u540e\u9762\u7b2c\u4e00\u4e2a\u5144\u5f1f\u8282\u70b9\u3002<\/span>find_next_siblings()\u8fd4\u56de\u540e\u9762\u6240\u6709\u5144\u5f1f\u8282\u70b9\uff0cfind_next_sibling()\u8fd4\u56de\u540e\u9762\u7b2c\u4e00\u4e2a\u5144\u5f1f\u8282\u70b9\u3002<\/span><\/p>\n

find_previous_siblings() find_previous_sibling()<\/h3>\n

find_previous_siblings() find_previous_sibling()<\/span>find_previous_siblings()\u8fd4\u56de\u524d\u9762\u6240\u6709\u5144\u5f1f\u8282\u70b9\uff0cfind_previous_sibling()\u8fd4\u56de\u524d\u9762\u7b2c\u4e00\u4e2a\u5144\u5f1f\u8282\u70b9\u3002<\/span>find_previous_siblings()\u8fd4\u56de\u524d\u9762\u6240\u6709\u5144\u5f1f\u8282\u70b9\uff0cfind_previous_sibling()\u8fd4\u56de\u524d\u9762\u7b2c\u4e00\u4e2a\u5144\u5f1f\u8282\u70b9\u3002<\/span><\/p>\n

find_all_next() find_next()<\/h3>\n

find_all_next() find_next()<\/span>find_all_next()\u8fd4\u56de\u8282\u70b9\u540e\u6240\u6709\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9, find_next()\u8fd4\u56de\u7b2c\u4e00\u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9<\/span>find_all_next()\u8fd4\u56de\u8282\u70b9\u540e\u6240\u6709\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9, find_next()\u8fd4\u56de\u7b2c\u4e00\u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9<\/span><\/p>\n

find_all_previous() \u548c find_previous()<\/h3>\n

find_all_previous() \u548c find_previous()<\/span>find_all_previous()\u8fd4\u56de\u8282\u70b9\u540e\u6240\u6709\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9, find_previous()\u8fd4\u56de\u7b2c\u4e00\u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9<\/span>find_all_previous()\u8fd4\u56de\u8282\u70b9\u540e\u6240\u6709\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9, find_previous()\u8fd4\u56de\u7b2c\u4e00\u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u8282\u70b9<\/span><\/p>\n

CSS\u9009\u62e9\u5668 \u7528select()<\/div>\n
soup.select(‘.panel-heading’) \u67e5\u627e\u7c7b\u540d\u4e3apanel-heading\u7684\u6807\u7b7e,\u8fd4\u56de\u5217\u8868<\/div>\n
soup.select(‘li’)[2]<\/div>\n
\u53ef\u4ee5\u8fdb\u884cfor<\/div>\n
for ul in soup.select(‘ul’):<\/div>\n
print(ul.select(‘li’))<\/div>\n
[<li class=”element”>Foo<\/li>, <li class=”element”>Bar<\/li>, <li class=”element”>Jay<\/li>] [<li class=”element”>Foo<\/li>, <li class=”element”>Bar<\/li>]<\/div>\n
\u83b7\u53d6\u5c5e\u6027\u503c<\/div>\n
for i in soup.select(‘ul’):<\/div>\n
print i[‘id’]<\/div>\n
\u8f93\u51fa<\/div>\n
list-1 list-2<\/div>\n
\u83b7\u53d6\u7b2c2\u4e2a\u5143\u7d20\u7684\u5c5e\u6027id\u503c<\/div>\n
soup.select(‘ul.list’)[1][‘id’]<\/div>\n
\u83b7\u53d6\u6807\u7b7e\u6587\u672c\u5185\u5bb9<\/div>\n
for li in soup.select(‘li’):<\/div>\n
print(li.get_text())<\/div>\n
soup.select(‘li’)[2].get_text()<\/div>\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

  \u89e3\u6790\u5668 \u4f7f\u7528\u65b9\u6cd5 \u4f18\u52bf \u52a3\u52bf Python\u6807\u51c6\u5e93 BeautifulSoup(markup, “html.parser”) Python\u7684\u5185\u7f6e\u6807\u51c6\u5e93\u3001\u6267\u884c\u901f\u5ea6\u9002\u4e2d \u3001\u6587\u6863\u5bb9\u9519\u80fd\u529b\u5f3a Python 2.7 […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[54],"tags":[115,116,76],"_links":{"self":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts\/1673"}],"collection":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1673"}],"version-history":[{"count":1,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts\/1673\/revisions"}],"predecessor-version":[{"id":1674,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts\/1673\/revisions\/1674"}],"wp:attachment":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1673"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1673"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1673"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}