首页 > 解决方案 > 抓取网站并下载excel报告python 3

问题描述

我试图废弃一个数据作为报告公开的网站,但在 HTML 网站结构中更深入,数据来自将报告嵌入 HTML 的 jQuery。这不允许我访问要下载的数据。

//<![CDATA[
Sys.Application.add_init(function() {
    $create(Telerik.Web.UI.RadComboBox, {"_dropDownAutoWidth":1,"_dropDownWidth":0,"_height":0,"_skin":"Bootstrap","_text":"English – United States","_uniqueId":"ctl00$eSSential_Header$eSSential_Login$ddlLanguage","_value":"en-US","clientStateFieldID":"ctl00_eSSential_Header_eSSential_Login_ddlLanguage_ClientState","collapseAnimation":"{\"duration\":450}","expandAnimation":"{\"duration\":450}","itemData":[{"value":"af"},{"value":"af-ZA"},{"value":"sq"},{"value":"sq-AL"},{"value":"ar"},{"value":"ar-DZ"},{"value":"ar-BH"},{"value":"ar-EG"},{"value":"ar-IQ"},{"value":"ar-JO"},{"value":"ar-KW"},{"value":"ar-LB"},{"value":"ar-LY"},{"value":"ar-MA"},{"value":"ar-OM"},{"value":"ar-QA"},{"value":"ar-SA"},{"value":"ar-SY"},{"value":"ar-TN"},{"value":"ar-AE"},{"value":"ar-YE"},{"value":"hy"},{"value":"hy-AM"},{"value":"az"},{"value":"az-AZ-Cyrl"},{"value":"az-AZ-Latn"},{"value":"eu"},{"value":"eu-ES"},{"value":"be"},{"value":"be-BY"},{"value":"bg"},{"value":"bg-BG"},{"value":"ca"},{"value":"ca-ES"},{"value":"zh-HK"},{"value":"zh-MO"},{"value":"zh-CN"},{"value":"zh-CHS"},{"value":"zh-SG"},{"value":"zh-TW"},{"value":"zh-CHT"},{"value":"hr"},{"value":"hr-HR"},{"value":"cs"},{"value":"cs-CZ"},{"value":"da"},{"value":"da-DK"},{"value":"div"},{"value":"div-MV"},{"value":"nl"},{"value":"nl-BE"},{"value":"nl-NL"},{"value":"en-AU"},{"value":"en-BZ"},{"value":"en-CA"},{"value":"en-CB"},{"value":"en-IE"},{"value":"en-JM"},{"value":"en-NZ"},{"value":"en-PH"},{"value":"en-ZA"},{"value":"en-TT"},{"value":"en-GB"},{"value":"en-US","selected":true},{"value":"en-ZW"},{"value":"et"},{"value":"et-EE"},{"value":"fo"},{"value":"fo-FO"},{"value":"fa"},{"value":"fa-IR"},{"value":"fi"},{"value":"fi-FI"},{"value":"fr"},{"value":"fr-BE"},{"value":"fr-CA"},{"value":"fr-FR"},{"value":"fr-LU"},{"value":"fr-MC"},{"value":"fr-CH"},{"value":"gl"},{"value":"gl-ES"},{"value":"ka"},{"value":"ka-GE"},{"value":"de"},{"value":"de-AT"},{"value":"de-DE"},{"value":"de-LI"},{"value":"de-LU"},{"value":"de-CH"},{"value":"el"},{"value":"el-GR"},{"value":"gu"},{"value":"gu-IN"},{"value":"he"},{"value":"he-IL"},{"value":"hi"},{"value":"hi-IN"},{"value":"hu"},{"value":"hu-HU"},{"value":"is"},{"value":"is-IS"},{"value":"id"},{"value":"id-ID"},{"value":"it"},{"value":"it-IT"},{"value":"it-CH"},{"value":"ja"},{"value":"ja-JP"},{"value":"kn"},{"value":"kn-IN"},{"value":"kk"},{"value":"kk-KZ"},{"value":"kok"},{"value":"kok-IN"},{"value":"ko"},{"value":"ko-KR"},{"value":"ky"},{"value":"ky-KG"},{"value":"lv"},{"value":"lv-LV"},{"value":"lt"},{"value":"lt-LT"},{"value":"mk"},{"value":"mk-MK"},{"value":"ms"},{"value":"ms-BN"},{"value":"ms-MY"},{"value":"mr"},{"value":"mr-IN"},{"value":"mn"},{"value":"mn-MN"},{"value":"no"},{"value":"nb-NO"},{"value":"nn-NO"},{"value":"pl"},{"value":"pl-PL"},{"value":"pt"},{"value":"pt-BR"},{"value":"pt-PT"},{"value":"pa"},{"value":"pa-IN"},{"value":"ro"},{"value":"ro-RO"},{"value":"ru"},{"value":"ru-RU"},{"value":"sa"},{"value":"sa-IN"},{"value":"sr-SP-Cyrl"},{"value":"sr-SP-Latn"},{"value":"sk"},{"value":"sk-SK"},{"value":"sl"},{"value":"sl-SI"},{"value":"es"},{"value":"es-AR"},{"value":"es-BO"},{"value":"es-CL"},{"value":"es-CO"},{"value":"es-CR"},{"value":"es-DO"},{"value":"es-EC"},{"value":"es-SV"},{"value":"es-GT"},{"value":"es-HN"},{"value":"es-MX"},{"value":"es-NI"},{"value":"es-PA"},{"value":"es-PY"},{"value":"es-PE"},{"value":"es-PR"},{"value":"es-ES"},{"value":"es-UY"},{"value":"es-VE"},{"value":"sw"},{"value":"sw-KE"},{"value":"sv"},{"value":"sv-FI"},{"value":"sv-SE"},{"value":"syr"},{"value":"syr-SY"},{"value":"ta"},{"value":"ta-IN"},{"value":"tt"},{"value":"tt-RU"},{"value":"te"},{"value":"te-IN"},{"value":"th"},{"value":"th-TH"},{"value":"tr"},{"value":"tr-TR"},{"value":"uk"},{"value":"uk-UA"},{"value":"ur"},{"value":"ur-PK"},{"value":"uz"},{"value":"uz-UZ-Cyrl"},{"value":"uz-UZ-Latn"},{"value":"vi"}],"localization":"{\"AllItemsCheckedString\":\"All items checked\",\"ItemsCheckedString\":\"items checked\",\"CheckAllString\":\"Check All\"}","selectedIndex":63}, null, null, $get("ctl00_eSSential_Header_eSSential_Login_ddlLanguage"));
});
Sys.Application.add_init(function() {
    $create(Telerik.Web.UI.RadTextBox, {"_displayText":"","_focused":true,"_initialValueAsText":"","_postBackEventReferenceScript":"setTimeout(\"__doPostBack(\\\u0027ctl00$eSSential_Header$eSSential_Login$txtLogin\\\u0027,\\\u0027\\\u0027)\", 0)","_skin":"Default","_validationText":"","clientStateFieldID":"ctl00_eSSential_Header_eSSential_Login_txtLogin_ClientState","enabled":true,"styles":{HoveredStyle: ["height:25px;width:131px;", "riTextBox riHover"],InvalidStyle: ["height:25px;width:131px;", "riTextBox riError"],DisabledStyle: ["height:25px;width:131px;", "riTextBox riDisabled"],FocusedStyle: ["height:25px;width:131px;", "riTextBox riFocused"],EmptyMessageStyle: ["height:25px;width:131px;", "riTextBox riEmpty"],ReadOnlyStyle: ["height:25px;width:131px;", "riTextBox riRead"],EnabledStyle: ["height:25px;width:131px;", "riTextBox riEnabled"]}}, null, null, $get("ctl00_eSSential_Header_eSSential_Login_txtLogin"));
});
Sys.Application.add_init(function() {
    $create(Telerik.Web.UI.RadTextBox, {"_focused":false,"_postBackEventReferenceScript":"setTimeout(\"__doPostBack(\\\u0027ctl00$eSSential_Header$eSSential_Login$txtPassword\\\u0027,\\\u0027\\\u0027)\", 0)","_skin":"Default","clientStateFieldID":"ctl00_eSSential_Header_eSSential_Login_txtPassword_ClientState","enabled":true,"styles":{HoveredStyle: ["height:25px;width:131px;", "riTextBox riHover"],InvalidStyle: ["height:25px;width:131px;", "riTextBox riError"],DisabledStyle: ["height:25px;width:131px;", "riTextBox riDisabled"],FocusedStyle: ["height:25px;width:131px;", "riTextBox riFocused"],EmptyMessageStyle: ["height:25px;width:131px;", "riTextBox riEmpty"],ReadOnlyStyle: ["height:25px;width:131px;", "riTextBox riRead"],EnabledStyle: ["height:25px;width:131px;", "riTextBox riEnabled"]}}, null, null, $get("ctl00_eSSential_Header_eSSential_Login_txtPassword"));
});
Sys.Application.add_init(function() {
    $create(Telerik.Web.UI.RadAjaxLoadingPanel, {"initialDelayTime":0,"isSticky":false,"minDisplayTime":0,"skin":"","uniqueID":"ctl00$cphInnerContent$RadAjaxLoadingPanel1","zIndex":90000}, null, null, $get("cphInnerContent_RadAjaxLoadingPanel1"));
});
//]]>
</script>
</form>
    <!-- jQuery (necessary for Bootstrap's JavaScript plugins) -->
    <script src="Script/AvalonScript.js"></script>
  <script>
      $(document).ready(function () {
          if ($("#stickyHeader") != null) {
              $("#stickyHeader").css("maxWidth", ($("#mainContent").width()));
          }
      });

      $(window).resize(function () {
          if ($("#stickyHeader").class = "affix") {
              $("#stickyHeader").css("maxWidth", ($("#mainContent").width()));
          }
      });
      $('#stickyHeader').affix({
          offset: {
              top: 90
          }
      });

网站上有一个选项可以将文件导出到 excel 中,但我不知道如何使用BeautifulSoupPython 3 中的任何其他库来完成此操作。

在此处输入图像描述

我很感激任何帮助。

谢谢

标签: pythonhtmlweb-scrapingbeautifulsoup

解决方案


推荐阅读