BeautifulSoup解析HTML

需要解析HTML源码里面的内容，包含特定标签和属性

<div class="file-source"><table><tr><th align="right">Line</th><th align="right">Branch</th><th align="right">Exec</th><th align="left">Source</th></tr><tr class="source-line"><td class="lineno"><a id="l1" href="#l1">1</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="c1">// RunAdder.cpp</span></td></tr><tr class="source-line"><td class="lineno"><a id="l2" href="#l2">2</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l3" href="#l3">3</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;iostream&gt;</span></td></tr><tr class="source-line"><td class="lineno"><a id="l4" href="#l4">4</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;unistd.h&gt;</span></td></tr><tr class="source-line"><td class="lineno"><a id="l5" href="#l5">5</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l6" href="#l6">6</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#ifdef GCOV</span></td></tr><tr class="source-line"><td class="lineno"><a id="l7" href="#l7">7</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="k">extern</span><span class="w"> </span><span class="s">&quot;C&quot;</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="n">__gcov_flush</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l8" href="#l8">8</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="k">extern</span><span class="w"> </span><span class="s">&quot;C&quot;</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="n">__gcov_dump</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l9" href="#l9">9</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="k">extern</span><span class="w"> </span><span class="s">&quot;C&quot;</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="n">__gcov_reset</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l10" href="#l10">10</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#endif </span><span class="c1">// TESTPLUS_GCOV</span></td></tr><tr class="source-line"><td class="lineno"><a id="l11" href="#l11">11</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l12" href="#l12">12</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#include</span><span class="w"> </span><span class="cpf">&quot;./include/Adder.h&quot;</span></td></tr><tr class="source-line"><td class="lineno"><a id="l13" href="#l13">13</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l14" href="#l14">14</a></td><td class="linebranch"></td><td class="linecount coveredLine">1</td><td class="src coveredLine"><span class="kt">int</span><span class="w"> </span><span class="nf">main</span><span class="p">()</span><span class="w"> </span><span class="p">{</span></td></tr><tr class="source-line"><td class="lineno"><a id="l15" href="#l15">15</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l16" href="#l16">16</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="w">    </span><span class="k">while</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span></td></tr><tr class="source-line"><td class="lineno"><a id="l17" href="#l17">17</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="w">    </span><span class="p">{</span></td></tr><tr class="source-line"><td class="lineno"><a id="l18" href="#l18">18</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l19" href="#l19">19</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">       </span><span class="n">printf</span><span class="p">(</span><span class="s">&quot;dump</span><span class="se">\n</span><span class="s">&quot;</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l20" href="#l20">20</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l21" href="#l21">21</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">        </span><span class="n">Adder</span><span class="w"> </span><span class="n">adder</span><span class="p">;</span></td></tr><tr class="source-line"><td class="lineno"><a id="l22" href="#l22">22</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">        </span><span class="n">adder</span><span class="p">.</span><span class="n">print_value</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">cout</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l23" href="#l23">23</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l24" href="#l24">24</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">        </span><span class="n">adder</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="mi">5</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l25" href="#l25">25</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">        </span><span class="n">adder</span><span class="p">.</span><span class="n">print_value</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">cout</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l26" href="#l26">26</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l27" href="#l27">27</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">        </span><span class="n">adder</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="mi">5</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l28" href="#l28">28</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">1/2</summary><div class="linebranchContents"><div class="takenBranch">&check; Branch 1 taken 1 times.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">        </span><span class="n">adder</span><span class="p">.</span><span class="n">print_value</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">cout</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l29" href="#l29">29</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="w">    </span></td></tr><tr class="source-line"><td class="lineno"><a id="l30" href="#l30">30</a></td><td class="linebranch"></td><td class="linecount coveredLine">1</td><td class="src coveredLine"><span class="w">        </span><span class="n">adder</span><span class="p">.</span><span class="n">clear</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l31" href="#l31">31</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l32" href="#l32">32</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="c1">// reference https://github.com/mongodb/mongo/blob/3adaac9be00bb0800184e0c27503c3d29c8e577e/src/mongo/util/quick_exit.cpp#L72</span></td></tr><tr class="source-line"><td class="lineno"><a id="l33" href="#l33">33</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="c1">// exit </span></td></tr><tr class="source-line"><td class="lineno"><a id="l34" href="#l34">34</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#ifdef TESTPLUS_GCOV</span></td></tr><tr class="source-line"><td class="lineno"><a id="l35" href="#l35">35</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#if (defined(__clang__) &amp;&amp; __clang_major__ &gt;= 12) || __GNUC__ &gt;= 11</span></td></tr><tr class="source-line"><td class="lineno"><a id="l36" href="#l36">36</a></td><td class="linebranch"><details class="linebranchDetails"><summary class="linebranchSummary">0/2</summary><div class="linebranchContents"><div class="notTakenBranch">&cross; Branch 1 not taken.</div><div class="notTakenBranch">&cross; Branch 2 not taken.</div></div></details></td><td class="linecount partialCoveredLine">1</td><td class="src partialCoveredLine"><span class="w">    </span><span class="n">__gcov_dump</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l37" href="#l37">37</a></td><td class="linebranch"></td><td class="linecount uncoveredLine">&cross;</td><td class="src uncoveredLine"><span class="w">    </span><span class="n">__gcov_reset</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l38" href="#l38">38</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#else</span></td></tr><tr class="source-line"><td class="lineno"><a id="l39" href="#l39">39</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="w">    </span><span class="n">__gcov_flush</span><span class="p">();</span></td></tr><tr class="source-line"><td class="lineno"><a id="l40" href="#l40">40</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#endif</span></td></tr><tr class="source-line"><td class="lineno"><a id="l41" href="#l41">41</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="cp">#endif </span><span class="c1">// TESTPLUS_GCOV</span></td></tr><tr class="source-line"><td class="lineno"><a id="l42" href="#l42">42</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l43" href="#l43">43</a></td><td class="linebranch"></td><td class="linecount uncoveredLine">&cross;</td><td class="src uncoveredLine"><span class="w">        </span><span class="n">sleep</span><span class="p">(</span><span class="mi">61</span><span class="p">);</span></td></tr><tr class="source-line"><td class="lineno"><a id="l44" href="#l44">44</a></td><td class="linebranch"></td><td class="linecount uncoveredLine">&cross;</td><td class="src uncoveredLine"><span class="w">    </span><span class="p">}</span></td></tr><tr class="source-line"><td class="lineno"><a id="l45" href="#l45">45</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr><tr class="source-line"><td class="lineno"><a id="l46" href="#l46">46</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="w">    </span><span class="k">return</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span></td></tr><tr class="source-line"><td class="lineno"><a id="l47" href="#l47">47</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "><span class="p">}</span></td></tr><tr class="source-line"><td class="lineno"><a id="l48" href="#l48">48</a></td><td class="linebranch"></td><td class="linecount "></td><td class="src "></td></tr></table>
</div>

BeautifulSoup

https://blog.csdn.net/naer_chongya/article/details/130633043
https://blog.51cto.com/u_13673090/2466801

安装

pip install BeautifulSoup4

demo.py解析Gcov工具生成html文件，主要思路是先观察HTML中我们需要提取信息数据的特征，找到特征之后利用BeautifulSoup的各种方法来遍历和查询HTML文档。
具体的使用方法前面两个链接介绍的较为详细。

from bs4 import BeautifulSoup
import json
import requestsheaders = {'accept': 'application/json','Content-Type': 'application/json',
}json_data = {'project_id': 'mecha','report_id': 314,'file_name': 'Game/AchievementMoudle/AchievementData.cpp',
}response = requests.post('http://10.11.00.00:0000/api/get/file', headers=headers, json=json_data)file_data = json.loads(response.text).get('data')src_code = []with open(r'D:/test/html_test/out.RunAdder.cpp.a9f32ea8f9bca6ced5ffba7e0bd94313.html') as f:# soup = BeautifulSoup(f.read(), 'html.parser')  # 读文件方式soup = BeautifulSoup(file_data, 'html.parser')  # 指定数据"str"# for child in soup.children:#     print(child)# 查找 标签为tr class为source-line的数据links = soup.find_all("tr", "source-line")# print(links)for link in links:# url = link.text# print(url.strip())src = link.find("td", "src")line_no = link.find("td", "lineno")line_count_coveredLine = link.find("td", "linecount coveredLine")line_count_partial_coveredLine = link.find("td", "linecount partialCoveredLine")line_count_uncoveredLine = link.find("td", "linecount uncoveredLine")src_code.append({"src": src.text.strip(),"line_no": int(line_no.text.strip()),"line_count_coveredLine": line_count_coveredLine.text.strip()if line_count_coveredLine else None,"line_count_partial_coveredLine": line_count_partial_coveredLine.text.strip()if line_count_partial_coveredLine else None,"line_count_uncoveredLine": line_count_uncoveredLine.text.strip()if line_count_uncoveredLine else None})print(src.text.strip())
function_name = "main"
function_line_no = 0
stack_list = []
function_end_line_no = 0for s in src_code:if function_name in s["src"]:function_line_no = s["line_no"]break# 括号匹配来找到指定函数的起始行号
for s in src_code:if s["line_no"] >= function_line_no:if "{" in s["src"]:stack_list.append("{")if "}" in s["src"]:stack_list.pop()if len(stack_list) == 0 and s["line_no"] != function_line_no:function_end_line_no = s["line_no"]breakprint(function_line_no)
print(function_end_line_no)cover_count = 0
uncover_count = 0if function_end_line_no:for s in src_code:if function_line_no <= s["line_no"] <= function_end_line_no:if s["line_count_coveredLine"] or s["line_count_partial_coveredLine"]:cover_count += 1if s["line_count_uncoveredLine"]:uncover_count += 1print(cover_count)
print(uncover_count)