{"id":877,"date":"2018-07-17T18:22:28","date_gmt":"2018-07-17T10:22:28","guid":{"rendered":"http:\/\/www.sniper97.cn\/?p=877"},"modified":"2018-07-17T18:22:28","modified_gmt":"2018-07-17T10:22:28","slug":"%e7%ac%ac%e4%ba%8c%e5%8d%81%e8%ae%b2%ef%bc%9a%e7%88%ac%e5%8f%96%e5%9b%be%e7%89%87","status":"publish","type":"post","link":"http:\/\/www.sniper97.cn\/index.php\/note\/python\/877\/","title":{"rendered":"\u7b2c\u4e8c\u5341\u8bb2\uff1a\u722c\u53d6\u56fe\u7247"},"content":{"rendered":"<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\"># -*- coding: utf-8 -*-\n# \u722c\u866b\u722c\u53d6\u56fe\u7247\nimport requests\nimport re\ndef crawl_image(image_url, image_local_path):\n    r = requests.get(image_url, stream=True)    # \u6253\u5f00\u6d41\n    with open(image_local_path, \"wb\") as f:    # \u6253\u5f00\u8def\u5f84  wb\u662f write binary\n        f.write(r.content)                      # with \u7c7b\u4f3c\u4e8etry catch  \u5e2e\u52a9\u89c4\u907f\u9519\u8bef\ndef crwal(page):\n    url = \"http:\/\/www.qiushibaike.com\/imgrank\/page\/\" + str(page)\n    res = requests.get(url)\n    # text \u8fd4\u56de\u7684\u662fUnicode\u7684\u6570\u636e\uff0c\u800ccontent\u8fd4\u56de\u7684\u662f\u4e8c\u8fdb\u5236\u6570\u636e\n    # decode \u4ee5\u9ed8\u8ba4\u7f16\u7801\u683c\u5f0f\u89e3\u7801\u5b57\u7b26\u4e32\uff0c\u9ed8\u8ba4\u7f16\u7801\u4e3a\u5b57\u7b26\u4e32\u7f16\u7801\n    content_list = re.findall(\"&lt;div class=\\\"thumb\\\"&gt;(.*?)&lt;\/div&gt;\", res.content.decode(\"utf-8\"), re.S)\n    # print(\"\\t\".join(content_list))\n    for content in content_list:\n        image_list = re.findall(\"&lt;img src=\\\"(.*?)\\\"\", content)\n        # print(\"\\t\".join(image_list))\n        for image_url in image_list:\n            crawl_image(\"http:\"+image_url, \".\/images\/\" + image_url.strip().split('\/')[-1])\nif __name__ == '__main__':\n    crwal(1)\n<\/pre>\n","protected":false},"excerpt":{"rendered":"<p># -*- coding: utf-8 -*- # \u722c\u866b\u722c\u53d6\u56fe\u7247 import requests i [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_mi_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[24],"tags":[],"views":4380,"_links":{"self":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/posts\/877"}],"collection":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/comments?post=877"}],"version-history":[{"count":0,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/posts\/877\/revisions"}],"wp:attachment":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/media?parent=877"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/categories?post=877"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/tags?post=877"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}