{"id":59,"date":"2014-06-23T15:05:20","date_gmt":"2014-06-23T15:05:20","guid":{"rendered":"http:\/\/ixyzero.com\/blog\/?p=59"},"modified":"2014-06-23T15:05:20","modified_gmt":"2014-06-23T15:05:20","slug":"%e6%96%b0%e6%b5%aa%e5%8d%9a%e5%ae%a2%e6%96%87%e7%ab%a0%e6%89%b9%e9%87%8f%e4%b8%8b%e8%bd%bd%e7%9a%84python%e8%84%9a%e6%9c%ac","status":"publish","type":"post","link":"https:\/\/ixyzero.com\/blog\/archives\/59.html","title":{"rendered":"\u65b0\u6d6a\u535a\u5ba2\u6587\u7ae0\u6279\u91cf\u4e0b\u8f7d\u7684Python\u811a\u672c"},"content":{"rendered":"
Update @ 2015-6-14<\/h6>\n

\u5efa\u8bae\u6709\u6279\u91cf\u4e0b\u8f7d\u65b0\u6d6a\u535a\u5ba2\u6587\u7ae0\u9700\u6c42\u7684\u540c\u5b66\u4f7f\u7528\u00a0https:\/\/github.com\/bfishadow\/SBB<\/a> \u6765\u8fdb\u884c\u64cd\u4f5c\uff0c\u4e00\u4e2a\u7b80\u5355\u7684Python\u811a\u672c\uff0c\u6ca1\u6709\u7528\u5230BeautifulSoup\uff0c\u751a\u81f3\u90fd\u6ca1\u6709\u7528re\uff0c\u4ec5\u4ec5\u4f9d\u9760urllib2\u6a21\u5757\u4e0b\u8f7d\uff0c\u7136\u540e\u5b57\u7b26\u4e32\u8fdb\u884c\u622a\u53d6\u64cd\u4f5c\u5c31\u53ef\u4ee5\u8fbe\u5230\u76f8\u540c\u7684\u76ee\u7684\uff0c\u901f\u5ea6\u4e5f\u6bd4\u8f83\u5feb\uff0c\u4e0d\u8fc7\u7f3a\u70b9\u5c31\u662f\u6ca1\u6709\u65b0\u5efa\u76ee\u5f55\u8fdb\u884c\u5b58\u653e\uff0c\u6240\u4ee5\u5728\u64cd\u4f5c\u7684\u65f6\u5019\u8981\u6ce8\u610f\u653e\u5728\u4e00\u4e2a\u5355\u72ec\u7684\u76ee\u5f55\u4e2d\u6267\u884c\uff1b\u6709\u80fd\u529b\u7684\u540c\u5b66\u53ef\u4ee5\u81ea\u884c\u4e0b\u8f7d\u8be5\u811a\u672c\u8fdb\u884c\u4e00\u4e9b\u4fee\u6539\uff0c\u6dfb\u52a0\/\u4fee\u6539\u4e00\u4e9b\u529f\u80fd\u65b9\u4fbf\u81ea\u5df1\u4f7f\u7528\u3002<\/p>\n

> python SBB.py http:\/\/blog.sina.com.cn\/chjguancha<\/pre>\n
\n
\u5728\u4e00\u4e2a\u5927\u725b\u7684blog\u91cc\u9762\u901b\u7684\u65f6\u5019\u770b\u5230\u4ed6\u4e4b\u524d\u5199\u7684\u8fd9\u4e2aPython\u6293\u53d6\u811a\u672c\uff0c\u89c9\u5f97\u6bd4\u8f83\u6709\u8da3\u800c\u4e14\u6709\u4e00\u5b9a\u5b9e\u9645\u610f\u4e49\uff0c\u5c31\u6536\u85cf\u4e86~~\u539f\u59cb\u7684\u811a\u672c\u56e0\u4e3a\u662f2012\u5e741\u6708\u4efd\u5de6\u53f3\u5199\u7684\uff0c\u73b0\u5728\u7684BeautifulSoup\u8fd9\u4e2a\u6a21\u5757\u4e5f\u6709\u4e86\u53d8\u5316\uff0c\u6240\u4ee5\u7a0d\u5fae\u4fee\u6539\u4e86\u4e00\u4e0b\uff0c\u671f\u95f4\u89e3\u51b3\u95ee\u9898\u7684\u8fc7\u7a0b\u503c\u5f97\u8bb0\u5f55\uff0c\u6240\u4ee5\u4e5f\u5c31\u4e00\u5e76\u53d1\u51fa\u6765\u4e86\uff0c\u505a\u4e2a\u8bb0\u5f55\uff1a<\/p>\n
\n
\u9996\u5148\uff0c\u539f\u6587\u94fe\u63a5\uff1a<\/h6>\n
\u65b0\u6d6a\u535a\u5ba2\u6279\u91cf\u4e0b\u8f7d<\/a>\uff1a\u6279\u91cf\u4e0b\u8f7d\u65b0\u6d6a\u535a\u5ba2\u7684\u6587\u7ae0<\/p>\n
\u5176\u6b21\uff0c\u5fae\u8c03\u540e\u7684\u4ee3\u7801\uff1a<\/h6>\n
#!\/usr\/bin\/env python\n# coding=utf-8\nimport urllib2\nimport sys, os\nimport re\nimport string\nfrom bs4 import BeautifulSoup\n\nreload(sys)\nsys.setdefaultencoding('utf8')\n\ndef encode(s):\n    return s.decode('utf-8').encode(sys.stdout.encoding, 'ignore')\n\ndef getHTML(url):\n    #proxy_handler = urllib2.ProxyHandler({'http':'http:\/\/211.138.124.211:80'})\n    #opener = urllib2.build_opener(proxy_handler)\n    #urllib2.install_opener(opener)\n    req = urllib2.Request(url)\n    response = urllib2.urlopen(req, timeout=15)\n    return BeautifulSoup(response)\n\ndef visible(element):\n    '''\u6293\u53d6\u53ef\u89c1\u7684\u6587\u672c\u5143\u7d20'''\n    if element.parent.name in ['style', 'script', '[document]', 'head', 'title']:\n        return False\n    elif re.match('<!--.*-->', str(element)):\n        return False\n    elif element == u'xa0':\n        return False\n    return True\n\ndef delReturn(element):\n    '''\u5220\u9664\u5143\u7d20\u5185\u7684\u6362\u884c'''\n    return re.sub('(?<!^)\\n+(?!$)', ' ', str(element)).decode('utf-8')\n\ndef validFilename(filename):\n    '''Windows'''\n    return re.sub('[\\\/:*?<>\"|\\xa0]', '', filename)\n\ndef writeToFile(text, filename, dirname):\n    if not os.path.exists(dirname):\n        os.makedirs(dirname)\n        print encode('\u4fdd\u5b58\u5230\u76ee\u5f55'), dirname\n\n    filename = validFilename(filename)\n    print encode('\u4fdd\u5b58\u6587\u7ae0'), filename\n\n    path = os.path.join(dirname, filename)\n    if not os.path.exists(path):\n        f = open(path, 'w')\n        f.write(text)\n        f.close()\n    else:\n        print filename, encode('\u5df2\u7ecf\u5b58\u5728')\n\ndef formatContent(url, title=''):\n    '''\u683c\u5f0f\u5316\u6587\u7ae0\u5185\u5bb9'''\n    page = getHTML(url)\n    content = page.find('div', {'class':'articalContent'})\n    art_id = re.search('blog_(\\w+)\\.html', url).group(1)\n    blog_name = str(page.find('title')).split('_')[-2]\n\n    if title == '':\n        title = str(page.find('title')).split('_')[0][7:]\n\n    temp_data = filter(visible, content.findAll(text=True)) # \u53bb\u6389\u4e0d\u53ef\u89c1\u5143\u7d20\n    temp_data = ''.join(map(delReturn, temp_data)) # \u5220\u9664\u5143\u7d20\u5185\u7684\u6362\u884c\u7b26\n    temp_data = temp_data.strip() # \u5220\u9664\u6587\u7ae0\u9996\u5c3e\u7684\u7a7a\u884c\n    temp_data = re.sub('\\n{2,}', '\\n\\n', temp_data) # \u5220\u9664\u6587\u7ae0\u5185\u8fc7\u591a\u7684\u7a7a\u884c\n\n    # \u8f93\u51fa\u5230\u6587\u4ef6\n    # \u7f16\u7801\u95ee\u9898\n    temp_data = '\u672c\u6587\u5730\u5740:'.decode('utf-8') + url + '\\n\\n' + temp_data\n    op_text = temp_data.encode('utf-8')\n    op_file = title + '_' + art_id +'.txt'\n\n    writeToFile(op_text, op_file, blog_name)\n\ndef articlelist(url):\n    articles = {}\n    page = getHTML(url)\n    pages = page.find('ul', {'class':'SG_pages'}).span.string\n    page_num = int(re.search('(\\d+)', pages).group(1))\n\n    for i in range(1, page_num+1):\n        print encode('\u751f\u6210\u7b2c%d\u9875\u6587\u7ae0\u7d22\u5f15'%i)\n        if i != 1:\n            url = re.sub('(_)\\d+(\\.html)$', '\\g<1>'+str(i)+'\\g<2>', url)\n            page = getHTML(url)\n\n        article = page.findAll('span', {'class':'atc_title'})\n        for art in article:\n            art_title = art.a['title']\n            art_href = art.a['href']\n            articles[art_title] = art_href\n\n    return articles\n\ndef blog_dld(articles):\n    if not isinstance(articles, dict):\n        return False\n    print encode('\u5f00\u59cb\u4e0b\u8f7d\u6587\u7ae0')\n    for art_title, art_href in articles.items():\n        formatContent(art_href, art_title)\n\nif __name__ == '__main__':\n    sel = raw_input(encode('\u4f60\u8981\u4e0b\u8f7d\u7684\u662f(1)\u5168\u90e8\u6587\u7ae0\u8fd8\u662f(2)\u5355\u7bc7\u6587\u7ae0\uff0c\u8f93\u51651\u6216\u80052: '))\n\n    if sel == '1':\n        #articlelist_url = 'http:\/\/blog.sina.com.cn\/s\/articlelist_1303481411_0_1.html'\n        articlelist_url = raw_input(encode('\u8bf7\u8f93\u5165\u535a\u5ba2\u6587\u7ae0\u76ee\u5f55\u94fe\u63a5: '))\n        articles = articlelist(articlelist_url)\n        blog_dld(articles)\n    else:\n        #article_url = 'http:\/\/blog.sina.com.cn\/s\/blog_4db18c430100gxc5.html'\n        article_url = raw_input(encode('\u8bf7\u8f93\u5165\u535a\u5ba2\u6587\u7ae0\u94fe\u63a5: '))\n        formatContent(article_url)<\/pre>\n
\u4ee5\u4e0b\u662f\u6211\u5f53\u65f6\u89e3\u51b3\u95ee\u9898\u7684\u8fc7\u7a0b\u8bb0\u5f55\uff1a<\/h5>\n
\u7b2c\u4e00\u6b21\u62a5\u9519\uff1aImportError: No module named BeautifulSoup<\/h6>\n
\u56e0\u4e3a\u65b0\u7248\u672c\u7684BeautifulSoup\u5df2\u7ecf\u4e0d\u518d\u547d\u540d\u4e3aBeautifulSoup\u4e86\uff0c\u800c\u662fbs4\uff0c\u6240\u4ee5\u9700\u8981\u5148\u4e0b\u8f7d\u5b89\u88c5bs4\u6a21\u5757\uff0c\u7136\u540e\u5728\u4ee3\u7801\u4e2d\u5c06\u5bf9\u5e94\u7684import\u547d\u4ee4\u4fee\u6539\u4e3a\uff1afrom bs4 import BeautifulSoup<\/p>\n
\u53c2\u8003\u6587\u7ae0\uff1a<\/strong><\/span><\/p>\n