{"id":1891,"date":"2019-01-29T11:16:57","date_gmt":"2020-02-12T13:55:58","guid":{"rendered":"http:\/\/vip.fxxkpython.com\/?p=1891"},"modified":"2020-02-12T21:56:00","modified_gmt":"2020-02-12T13:56:00","slug":"0bc221da42","status":"publish","type":"post","link":"https:\/\/vip.fxxkpython.com\/?p=1891","title":{"rendered":"python\u722c\u866b07 | \u6709\u4e86 BeautifulSoup \uff0c\u5988\u5988\u518d\u4e5f\u4e0d\u7528\u62c5\u5fc3\u6211\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u4e86"},"content":{"rendered":"
\n

\u6211\u4eec\u4e0a\u6b21\u505a\u4e86<\/p>\n


<\/p>\n

\u4f60\u7684\u7b2c\u4e00\u4e2a\u722c\u866b\uff0c\u722c\u53d6\u5f53\u5f53\u7f51 Top 500 \u672c\u4e94\u661f\u597d\u8bc4\u4e66\u7c4d<\/a>
<\/p>\n


<\/p>\n

\u6709\u4e9b\u670b\u53cb\u89c9\u5f97
<\/p>\n


<\/p>\n

\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f<\/a>\u53bb\u63d0\u53d6\u4fe1\u606f<\/p>\n


<\/p>\n

\u592a\u7279\u4e48\u9ebb\u70e6\u4e86<\/p>\n


<\/p>\n

\"python\"<\/p>\n


<\/p>\n

\u6709\u6ca1\u6709\u4ec0\u4e48\u522b\u7684\u65b9\u5f0f<\/p>\n


<\/p>\n

\u66f4\u65b9\u4fbf\u8fc7\u6ee4\u6211\u4eec\u60f3\u8981\u7684\u5185\u5bb9\u554a<\/p>\n


<\/p>\n

emmmm<\/p>\n


<\/p>\n

\u4f60\u8fd8\u522b\u8bf4<\/p>\n


<\/p>\n

\u8fd8\u771f\u6709<\/p>\n


<\/p>\n

\u6709\u4e00\u4e2a\u9ad8\u6548\u7684\u7f51\u9875\u89e3\u6790\u5e93<\/p>\n


<\/p>\n

\u5b83\u7684\u540d\u5b57\u53eb\u505a<\/p>\n


<\/p>\n

BeautifulSoup<\/strong><\/p>\n


<\/p>\n


<\/p>\n

\u90a3\u53ef\u662f<\/p>\n


<\/p>\n

\"python\"<\/p>\n


<\/strong><\/p>\n

\u5b83<\/p>\n


<\/strong><\/p>\n

\u662f\u4e00\u4e2a\u53ef\u4ee5\u4ece HTML \u6216 XML \u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\u7684 Python \u5e93<\/p>\n


<\/p>\n

\u90a3\u4e48\u8fd9\u4e48\u73a9\u5462
<\/p>\n


<\/p>\n

…<\/p>\n


<\/p>\n


<\/p>\n

\u63a5\u4e0b\u6765\u5c31\u662f<\/p>\n


<\/p>\n

\u5b66\u4e60python\u7684\u6b63\u786e\u59ff\u52bf<\/strong><\/p>\n


<\/strong><\/p>\n

\"python\"<\/strong><\/p>\n


<\/strong><\/p>\n


<\/strong><\/p>\n

\u9996\u5148\u6211\u4eec\u8981\u5b89\u88c5\u4e00\u4e0b\u8fd9\u4e2a\u5e93<\/p>\n


<\/p>\n

pip install beautifulsoup4<\/p>\n


<\/p>\n

beautifulsoup\u652f\u6301\u4e0d\u540c\u7684\u89e3\u6790\u5668<\/span><\/p>\n


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

\u6bd4\u5982<\/span><\/p>\n


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

\u5bf9 HTML \u7684\u89e3\u6790<\/span><\/p>\n


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

\u5bf9 XML \u7684\u89e3\u6790<\/span><\/p>\n


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

\u5bf9 HTML5 \u7684\u89e3\u6790<\/span><\/p>\n


<\/p>\n

\u4f60\u770b<\/p>\n


<\/p>\n

\"python\"<\/p>\n

\n

\u4e00\u822c\u60c5\u51b5\u4e0b<\/p>\n


<\/p>\n

\u6211\u4eec\u7528\u7684\u6bd4\u8f83\u591a\u7684\u662f lxml \u89e3\u6790\u5668<\/p>\n


<\/p>\n

\u6211\u4eec\u5148\u6765\u4f7f\u7528\u4e00\u4e2a\u4f8b\u5b50<\/p>\n


<\/p>\n

\u8ba9\u4f60\u4f53\u9a8c\u4e00\u4e0b<\/p>\n


<\/p>\n

beautifulsoup \u7684\u4e00\u4e9b\u5e38\u7528\u7684\u65b9\u6cd5<\/span><\/p>\n


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

\u53ef\u6d41\u5f0a\u4e86\u5462<\/p>\n


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

\"python\"<\/span><\/p>\n


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

\u6bd4\u5982\u6211\u4eec\u6709\u8fd9\u6837\u4e00\u6bb5 HTML \u4ee3\u7801<\/span><\/p>\n


<\/p>\n

\n
html_doc = \"\"\"

<html<\/span>><\/span><head<\/span>><\/span><title<\/span>><\/span>\u5b66\u4e60python\u7684\u6b63\u786e\u59ff\u52bf<\/title<\/span>><\/span><\/head<\/span>><\/span>
<body<\/span>><\/span>
<p<\/span> class<\/span>=\"title\"<\/span>><\/span><b<\/span>><\/span>\u5c0f\u5e05b\u7684\u6545\u4e8b<\/b<\/span>><\/span><\/p<\/span>><\/span>

<p<\/span> class<\/span>=\"story\"<\/span>><\/span>\u6709\u4e00\u5929\uff0c\u5c0f\u5e05b\u60f3\u7ed9\u5927\u5bb6\u8bb2\u4e24\u4e2a\u7b11\u8bdd
<a<\/span> href<\/span>=\"http:\/\/example.com\/1\"<\/span> class<\/span>=\"sister\"<\/span> id<\/span>=\"link1\"<\/span>><\/span>\u4e00\u4e2a\u7b11\u8bdd\u957f<\/a<\/span>><\/span>,
<a<\/span> href<\/span>=\"http:\/\/example.com\/2\"<\/span> class<\/span>=\"sister\"<\/span> id<\/span>=\"link2\"<\/span>><\/span>\u4e00\u4e2a\u7b11\u8bdd\u77ed<\/a<\/span>><\/span> ,
\u4ed6\u95ee\u5927\u5bb6\uff0c\u60f3\u542c\u957f\u7684\u8fd8\u662f\u77ed\u7684\uff1f<\/p<\/span>><\/span>

<p<\/span> class<\/span>=\"story\"<\/span>><\/span>...<\/p<\/span>><\/span>

\"\"\"<\/code><\/pre>\n<\/section>\n
<\/span><\/p>\n
\u5728\u4e0d\u4f7f\u7528 re \u6765\u8fdb\u884c\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u60c5\u51b5\u4e0b<\/span><\/p>\n

<\/span><\/p>\n
\u5982\u4f55\u5feb\u901f\u83b7\u53d6\u5230\u6211\u4eec\u60f3\u8981\u7684\u5185\u5bb9\u5462\uff1f<\/span><\/p>\n

<\/span><\/p>\n
\u5148\u5b89\u88c5<\/span>\u4e00\u4e0b<\/span><\/p>\n

<\/span><\/p>\n
pip install beautifulsoup4<\/span><\/p>\n
pip install lxml<\/span><\/p>\n
<\/span>
<\/p>\n
\u63a5\u7740\u5c06 html \u7684\u6e90\u4ee3\u7801\u4f20\u7ed9 BeautifulSoup<\/span><\/p>\n

<\/span><\/p>\n
\n
soup = BeautifulSoup(html_doc,'lxml')<\/span><\/code><\/pre>\n<\/section>\n
<\/span>
<\/p>\n

<\/p>\n
\u6b64\u65f6\u6b64\u523b<\/p>\n

<\/p>\n
\u5c31\u4e0d\u9700\u8981\u81ea\u5df1\u5199\u6b63\u5219\u5339\u914d\u4e86<\/p>\n

<\/p>\n
\"python\"<\/p>\n

<\/p>\n
\u6211\u4eec\u8981\u505a\u7684\u5c31\u662f\u4ece\u8fd9\u4e2a\u5bf9\u8c61\u76f4\u63a5\u83b7\u53d6<\/strong>\u6211\u4eec\u8981\u7684\u5185\u5bb9<\/p>\n

<\/p>\n
\u83b7\u53d6\u6807\u9898\u7684\u5185\u5bb9<\/p>\n

<\/p>\n
\n
print<\/span>(soup.title.string<\/span>)
#\u5b66\u4e60python\u7684\u6b63\u786e\u59ff\u52bf<\/code><\/pre>\n<\/section>\n

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

<\/span><\/p>\n
\u83b7\u53d6 p \u6807\u7b7e\u91cc\u9762\u7684\u5185\u5bb9<\/span><\/p>\n

<\/span><\/p>\n
\n
print<\/span>(soup.p<\/span>.string<\/span>)
#\u5c0f\u5e05b<\/span>\u7684\u6545\u4e8b<\/code><\/pre>\n<\/section>\n
<\/span>
<\/p>\n
\u83b7\u53d6 title \u7684\u7236\u7ea7\u6807\u7b7e<\/p>\n

<\/p>\n
\n
print<\/span>(soup<\/span>.title<\/span>.parent<\/span>.name<\/span>)
#head<\/span><\/code><\/pre>\n<\/section>\n

<\/span><\/p>\n
\u83b7\u53d6\u8d85\u94fe\u63a5<\/span><\/p>\n

<\/span><\/p>\n
\n
print(soup.a)
#<\/span><a class=\"sister\"<\/span> href=\"http:\/\/example.com\/1\"<\/span> id=\"link1\"<\/span>>\u4e00\u4e2a\u7b11\u8bdd\u957f<\/a><\/span><\/code><\/pre>\n<\/section>\n
<\/span>
<\/p>\n
\u83b7\u53d6\u6240\u6709\u8d85\u94fe\u63a5<\/p>\n

<\/p>\n
\n
print(soup.find_all('a'))
#[<a<\/span> class<\/span>=\"sister\"<\/span> href<\/span>=\"http:\/\/example.com\/1\"<\/span> id<\/span>=\"link1\"<\/span>><\/span>\u4e00\u4e2a\u7b11\u8bdd\u957f<\/a<\/span>><\/span>, <a<\/span> class<\/span>=\"sister\"<\/span> href<\/span>=\"http:\/\/example.com\/2\"<\/span> id<\/span>=\"link2\"<\/span>><\/span>\u4e00\u4e2a\u7b11\u8bdd\u77ed<\/a<\/span>><\/span>]<\/code><\/pre>\n<\/section>\n

<\/p>\n
\u83b7\u53d6 id \u4e3a link2 \u7684\u8d85\u94fe\u63a5<\/p>\n

<\/p>\n
\n
print<\/span>(soup.find<\/span>(id=\"link2\"<\/span>))
#<a<\/span> class=\"sister\"<\/span> href=\"http:\/\/example.com\/2\"<\/span> id=\"link2\"<\/span>>\u4e00\u4e2a\u7b11\u8bdd\u77ed<\/a<\/span>><\/code><\/pre>\n<\/section>\n

<\/p>\n

<\/p>\n
\u83b7\u53d6\u7f51\u9875\u4e2d\u6240\u6709\u7684\u5185\u5bb9<\/p>\n

<\/p>\n
\n
print<\/span>(soup.get_text())

# \u5b66\u4e60python<\/span>\u7684\u6b63\u786e\u59ff\u52bf

\u5c0f\u5e05b<\/span>\u7684\u6545\u4e8b
\u6709\u4e00\u5929\uff0c\u5c0f\u5e05b<\/span>\u60f3\u7ed9\u5927\u5bb6\u8bb2\u4e24\u4e2a\u7b11\u8bdd
\u4e00\u4e2a\u7b11\u8bdd\u957f,
\u4e00\u4e2a\u7b11\u8bdd\u77ed ,
\u4ed6\u95ee\u5927\u5bb6\uff0c\u60f3\u542c\u957f\u7684\u8fd8\u662f\u77ed\u7684\uff1f
...<\/code><\/pre>\n<\/section>\n

<\/p>\n

<\/p>\n
\u9664\u4e86find\u65b9\u6cd5\u4e4b\u5916<\/p>\n

<\/p>\n
\u5982\u679c\u4f60\u5bf9css\u6bd4\u8f83\u719f\u6089<\/p>\n

<\/p>\n
\u4e5f\u53ef\u4ee5\u4f7f\u7528 select \u65b9\u6cd5<\/p>\n

<\/p>\n
\n
soup = BeautifulSoup(html_doc,'lxml'<\/span>)

print<\/span>(soup.select<\/span>(\"title\"<\/span>))
print<\/span>(soup.select<\/span>(\"body a\"<\/span>))
print<\/span>(soup.select<\/span>(\"p > #link1\"<\/span>))<\/code><\/pre>\n<\/section>\n

<\/p>\n

<\/p>\n
\u4ee5\u4e0a\u5c31\u662f BeautifulSoup \u5e38\u7528\u7684\u65b9\u6cd5<\/span><\/p>\n

<\/span><\/p>\n
\u60f3\u8fdb\u4e00\u6b65\u4e86\u89e3\u53ef\u4ee5\u5230\u8fd9<\/span><\/p>\n

<\/span><\/p>\n
https:\/\/www.crummy.com\/software\/BeautifulSoup\/bs4\/doc\/<\/span><\/p>\n

<\/span><\/p>\n
\u6709\u4e86\u5b83<\/p>\n

<\/p>\n
\u5988\u5988\u518d\u4e5f\u4e0d\u7528\u62c5\u5fc3\u6211\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u4e86<\/p>\n

<\/p>\n
\u4e0b\u6b21\u8fd8\u6709\u4eba\u8fd9\u6837\u95ee\u4f60<\/p>\n

<\/p>\n
\u5e74\u8f7b\u4eba\uff0c\u4e0d\u4f1a\u6b63\u5219\u8868\u8fbe\u5f0f\u4f60\u7761\u5f97\u7740\u89c9\uff1f\u6709\u70b9\u51fa\u606f\u6ca1\u6709\uff1f<\/a>
<\/p>\n

<\/p>\n
\u4f60\u53ef\u4ee5\u50b2\u5a07\u7684\u544a\u8bc9\u4ed6<\/p>\n

<\/p>\n
\"python\"<\/p>\n

<\/p>\n

<\/p>\n
\u7761\u5f97\u7740<\/strong><\/p>\n

<\/p>\n

<\/p>\n
\u672c\u7bc7\u5b8c<\/p>\n

<\/p>\n
\u518d\u89c1<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n
\u8fd1\u671f\u6587\u7ae0<\/p>\n

<\/p>\n
python\u722c\u866b06 | \u4f60\u7684\u7b2c\u4e00\u4e2a\u722c\u866b\uff0c\u722c\u53d6\u5f53\u5f53\u7f51 Top 500 \u672c\u4e94\u661f\u597d\u8bc4\u4e66\u7c4d<\/a>
<\/p>\n

<\/p>\n
python\u722c\u866b05 | \u5e74\u8f7b\u4eba\uff0c\u4e0d\u4f1a\u6b63\u5219\u8868\u8fbe\u5f0f\u4f60\u7761\u5f97\u7740\u89c9\uff1f\u6709\u70b9\u51fa\u606f\u6ca1\u6709\uff1f<\/a>
<\/p>\n

<\/p>\n
python\u722c\u866b04 | \u957f\u6c5f\u540e\u6d6a\u63a8\u524d\u6d6a\uff0cReuqests\u5e93\u628aurllib\u5e93\u62cd\u5728\u6c99\u6ee9\u4e0a<\/a>
<\/p>\n

<\/p>\n

<\/p>\n
\"python\"<\/p>\n
\u626b\u4e00\u626b<\/span><\/strong><\/p>\n
\u5b66\u4e60 Python \u6ca1\u70e6\u607c<\/span><\/strong><\/p>\n

<\/span><\/strong><\/p>\n
\"python\"<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n
\u597d\u770b\u7684\u4eba\u90fd\u70b9\u4e86<\/p>\n
\n
\u539f\u6587\u59cb\u53d1\u4e8e\u5fae\u4fe1\u516c\u4f17\u53f7\uff08\u5b66\u4e60python\u7684\u6b63\u786e\u59ff\u52bf\uff09\uff1apython<\/a><\/p>\n<\/blockquote>\n<\/div>\n","protected":false},"excerpt":{"rendered":"
\u6211\u4eec\u4e0a\u6b21\u505a\u4e86 \u4f60\u7684\u7b2c\u4e00\u4e2a\u722c\u866b\uff0c\u722c\u53d6\u5f53\u5f53\u7f51 Top 500 \u672c\u4e94\u661f\u597d\u8bc4\u4e66\u7c4d \u6709\u4e9b\u670b\u53cb\u89c9\u5f97 \u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u53bb\u63d0\u53d6\u4fe1\u606f \u592a\u7279\u4e48\u9ebb\u70e6\u4e86 \u6709\u6ca1\u6709\u4ec0\u4e48\u522b\u7684\u65b9\u5f0f \u66f4\u65b9\u4fbf\u8fc7\u6ee4\u6211\u4eec\u60f3\u8981\u7684\u5185\u5bb9\u554a emmmm \u4f60\u8fd8\u522b\u8bf4 \u8fd8\u771f\u6709 \u6709\u4e00\u4e2a\u9ad8\u6548\u7684\u7f51\u9875\u89e3\u6790\u5e93 \u5b83\u7684\u540d\u5b57\u53eb\u505a Bea…<\/p>\n","protected":false},"author":1,"featured_media":1892,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[303],"tags":[302,19,300,301],"_links":{"self":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts\/1891"}],"collection":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1891"}],"version-history":[{"count":1,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts\/1891\/revisions"}],"predecessor-version":[{"id":1902,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts\/1891\/revisions\/1902"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/media\/1892"}],"wp:attachment":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1891"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1891"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1891"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}