w

Author: JCfly3000

_freeze/other/2 web scrap/3 web scrap advance/execute-results/html.json

@@ -2,7 +2,7 @@
   "hash": "305af435316331b72089721c1f0d43bb",
   "result": {
     "engine": "jupyter",
-    "markdown": "---\ntitle: \"web scrap with advance\"\nauthor: \"Tony Duan\"\n\nexecute:\n  warning: false\n  error: false\n  eval: false\n\nformat:\n  html:\n    toc: true\n    toc-location: right\n    code-fold: show\n    code-tools: true\n    number-sections: true\n    code-block-bg: true\n    code-block-border-left: \"#31BAE9\"\n---\n\n::: {#920f4433 .cell execution_count=1}\n``` {.python .cell-code}\nfrom seleniumbase import SB\n\nwith SB(test=True, uc=True) as sb:\n    sb.open(\"https://google.com/ncr\")\n    sb.type('[title=\"Search\"]', \"SeleniumBase GitHub page\\n\")\n    sb.click('[href*=\"github.com/seleniumbase/\"]')\n    sb.save_screenshot_to_logs()  # ./latest_logs/\n    print(sb.get_page_title())\n```\n:::\n\n\n::: {#f412b7cd .cell execution_count=2}\n``` {.python .cell-code}\nfrom seleniumbase import SB\n\nwith SB(test=True, uc=True) as sb:\n    sb.open(\"https://www.whiskybase.com/whiskies/\")\n    #sb.type('[title=\"Search\"]', \"SeleniumBase GitHub page\\n\")\n    #sb.click('[href*=\"github.com/seleniumbase/\"]')\n    sb.save_screenshot_to_logs()  # ./latest_logs/\n    print(sb.get_page_title())\n```\n:::\n\n\n::: {#72338001 .cell execution_count=3}\n``` {.python .cell-code}\nfrom seleniumbase import Driver\nclass Scraper(BaseCase):\ndef test_bypass_bot_protection(self):\ndriver = Driver(uc=True)\ndriver.open(\"https://www.whiskybase.com/whiskies/whisky/268484/2009-ud\")\ndriver.uc_gui_click_captcha()\npage_html = driver.get_page_source()\nprint(page_html)\ndriver.quit()\n```\n:::\n\n\n::: {#c5151c77 .cell execution_count=4}\n``` {.python .cell-code}\nfrom bs4 import BeautifulSoup\nsoup = BeautifulSoup(page_html, 'html.parser')\nprint(soup.prettify())\n```\n:::\n\n\n::: {#ac55c2eb .cell execution_count=5}\n``` {.python .cell-code}\nprint(soup.get_text())\n```\n:::\n\n\n::: {#326d7d98 .cell execution_count=6}\n``` {.python .cell-code}\nsoup.select(\".votes-rating-current\").text\n```\n:::\n\n\nh1\n\n# Reference:\n\nhttps://github.com/seleniumbase/SeleniumBase\n\nhttps://medium.com/@datajournal/web-scraping-with-seleniumbase-e3ead6aebe7f\n\nhttps://github.com/ultrafunkamsterdam/undetected-chromedriver\n\n",
+    "markdown": "---\ntitle: \"web scrap with advance\"\nauthor: \"Tony Duan\"\n\nexecute:\n  warning: false\n  error: false\n  eval: false\n\nformat:\n  html:\n    toc: true\n    toc-location: right\n    code-fold: show\n    code-tools: true\n    number-sections: true\n    code-block-bg: true\n    code-block-border-left: \"#31BAE9\"\n---\n\n::: {#f4664121 .cell execution_count=1}\n``` {.python .cell-code}\nfrom seleniumbase import SB\n\nwith SB(test=True, uc=True) as sb:\n    sb.open(\"https://google.com/ncr\")\n    sb.type('[title=\"Search\"]', \"SeleniumBase GitHub page\\n\")\n    sb.click('[href*=\"github.com/seleniumbase/\"]')\n    sb.save_screenshot_to_logs()  # ./latest_logs/\n    print(sb.get_page_title())\n```\n:::\n\n\n::: {#27ca28e0 .cell execution_count=2}\n``` {.python .cell-code}\nfrom seleniumbase import SB\n\nwith SB(test=True, uc=True) as sb:\n    sb.open(\"https://www.whiskybase.com/whiskies/\")\n    #sb.type('[title=\"Search\"]', \"SeleniumBase GitHub page\\n\")\n    #sb.click('[href*=\"github.com/seleniumbase/\"]')\n    sb.save_screenshot_to_logs()  # ./latest_logs/\n    print(sb.get_page_title())\n```\n:::\n\n\n::: {#b67fbc70 .cell execution_count=3}\n``` {.python .cell-code}\nfrom seleniumbase import Driver\nclass Scraper(BaseCase):\ndef test_bypass_bot_protection(self):\ndriver = Driver(uc=True)\ndriver.open(\"https://www.whiskybase.com/whiskies/whisky/268484/2009-ud\")\ndriver.uc_gui_click_captcha()\npage_html = driver.get_page_source()\nprint(page_html)\ndriver.quit()\n```\n:::\n\n\n::: {#9e078a79 .cell execution_count=4}\n``` {.python .cell-code}\nfrom bs4 import BeautifulSoup\nsoup = BeautifulSoup(page_html, 'html.parser')\nprint(soup.prettify())\n```\n:::\n\n\n::: {#d632b64c .cell execution_count=5}\n``` {.python .cell-code}\nprint(soup.get_text())\n```\n:::\n\n\n::: {#203c4ca5 .cell execution_count=6}\n``` {.python .cell-code}\nsoup.select(\".votes-rating-current\").text\n```\n:::\n\n\nh1\n\n# Reference:\n\nhttps://github.com/seleniumbase/SeleniumBase\n\nhttps://medium.com/@datajournal/web-scraping-with-seleniumbase-e3ead6aebe7f\n\nhttps://github.com/ultrafunkamsterdam/undetected-chromedriver\n\n",
     "supporting": [
       "3 web scrap advance_files"
     ],

docs/Publish/5 git/git.html

@@ -272,7 +272,7 @@
  <span class="dropdown-text">1 google analytics</span></a>
   </li>  
         <li>
-    <a class="dropdown-item" href="../../other/2 web scrap/web scrap.html">
+    <a class="dropdown-item" href="../../other/2 web scrap/1 web scrap with rvest.html">
  <span class="dropdown-text">2 web scrap</span></a>
   </li>  
         <li>

docs/other/2 web scrap/3 web scrap advance.html

@@ -429,7 +429,7 @@ <h2 id="toc-title">On this page</h2>
 </header>
 
 
-<div id="920f4433" class="cell" data-execution_count="1">
+<div id="f4664121" class="cell" data-execution_count="1">
 <details open="" class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> seleniumbase <span class="im">import</span> SB</span>
@@ -442,7 +442,7 @@ <h2 id="toc-title">On this page</h2>
 <span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a>    <span class="bu">print</span>(sb.get_page_title())</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="f412b7cd" class="cell" data-execution_count="2">
+<div id="27ca28e0" class="cell" data-execution_count="2">
 <details open="" class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> seleniumbase <span class="im">import</span> SB</span>
@@ -455,7 +455,7 @@ <h2 id="toc-title">On this page</h2>
 <span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a>    <span class="bu">print</span>(sb.get_page_title())</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="72338001" class="cell" data-execution_count="3">
+<div id="b67fbc70" class="cell" data-execution_count="3">
 <details open="" class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> seleniumbase <span class="im">import</span> Driver</span>
@@ -469,21 +469,21 @@ <h2 id="toc-title">On this page</h2>
 <span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a>driver.quit()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="c5151c77" class="cell" data-execution_count="4">
+<div id="9e078a79" class="cell" data-execution_count="4">
 <details open="" class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> bs4 <span class="im">import</span> BeautifulSoup</span>
 <span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a>soup <span class="op">=</span> BeautifulSoup(page_html, <span class="st">'html.parser'</span>)</span>
 <span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(soup.prettify())</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="ac55c2eb" class="cell" data-execution_count="5">
+<div id="d632b64c" class="cell" data-execution_count="5">
 <details open="" class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(soup.get_text())</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="326d7d98" class="cell" data-execution_count="6">
+<div id="203c4ca5" class="cell" data-execution_count="6">
 <details open="" class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>soup.select(<span class="st">".votes-rating-current"</span>).text</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>

docs/other/6 other/1 chromote.html

@@ -270,7 +270,7 @@
  <span class="dropdown-text">1 google analytics</span></a>
   </li>  
         <li>
-    <a class="dropdown-item" href="../../other/2 web scrap/web scrap.html">
+    <a class="dropdown-item" href="../../other/2 web scrap/1 web scrap with rvest.html">
  <span class="dropdown-text">2 web scrap</span></a>
   </li>  
         <li>
@@ -344,8 +344,20 @@
       <ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth2 show">  
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
-  <a href="../../other/2 web scrap/web scrap.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">web scrap</span></a>
+  <a href="../../other/2 web scrap/1 web scrap with rvest.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">web scrap with rvest</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../other/2 web scrap/2 web scrap with chromote.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">web scrap with chromote</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../other/2 web scrap/3 web scrap advance.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">web scrap with advance</span></a>
   </div>
 </li>
       </ul>