Scraping, Plotly example rewrite

2 months ago · 3d17eeb4fb
2 changed files with 66 additions and 46 deletions
--- a/README.md
+++ b/README.md
@ -2510,10 +2510,9 @@ document   = bs4.BeautifulSoup(response.text, 'html.parser')
 table      = document.find('table', class_='infobox vevent')
 python_url = table.find('th', text='Website').next_sibling.a['href']
 logo_url   = table.find('img')['src']
 logo       = requests.get(f'https:{logo_url}').content
 filename   = os.path.basename(logo_url)
 with open(filename, 'wb') as file:
    file.write(logo)
    file.write(requests.get(f'https:{logo_url}').content)
 print(f'{python_url}, file://{os.path.abspath(filename)}')
 ```
@ -2525,6 +2524,7 @@ from selenium import webdriver
 <WebDrv> = webdriver.Chrome/Firefox/Safari/Edge()     # Opens a browser. Also <WebDrv>.quit().
 <WebDrv>.get('<url>')                                 # Also <WebDrv>.implicitly_wait(seconds).
 <str>  = <WebDrv>.page_source                         # Returns HTML of fully rendered page.
 <El>   = <WebDrv/El>.find_element('css selector', …)  # '<tag>#<id>.<class>[<attr>="<val>"]…'.
 <list> = <WebDrv/El>.find_elements('xpath', …)        # '//<tag>[@<attr>="<val>"]…'. See XPath.
 <str>  = <El>.get_attribute(<str>)                    # Property if exists. Also <El>.text.
@ -3457,32 +3457,41 @@ px.line(df, x='Date', y='Total Deaths per Million', color='Continent').show()
 <div id="e23ccacc-a456-478b-b467-7282a2165921" class="plotly-graph-div" style="height:287px; width:935px;"></div>
 ```python
 import pandas as pd, plotly.graph_objects as go
 # $ pip3 install pandas selenium plotly lxml
 import pandas as pd, selenium.webdriver, plotly.graph_objects as go
 def main():
    covid, bitcoin, gold, dow = scrape_data()
    covid, (bitcoin, gold, dow) = get_covid_cases(), get_tickers()
    df = wrangle_data(covid, bitcoin, gold, dow)
    display_data(df)
 def scrape_data():
    def get_covid_cases():
        url = 'https://covid.ourworldindata.org/data/owid-covid-data.csv'
        df = pd.read_csv(url, usecols=['location', 'date', 'total_cases'])
        df = df[df.location == 'World']
        return df.set_index('date').total_cases
    def get_ticker(symbol):
        url = (f'https://query1.finance.yahoo.com/v7/finance/download/{symbol}?'
               'period1=1579651200&period2=9999999999&interval=1d&events=history')
        df = pd.read_csv(url, usecols=['Date', 'Close'])
        return df.set_index('Date').Close
    out = get_covid_cases(), get_ticker('BTC-USD'), get_ticker('GC=F'), get_ticker('^DJI')
    names = ['Total Cases', 'Bitcoin', 'Gold', 'Dow Jones']
    return map(pd.Series.rename, out, names)
 def get_covid_cases():
    url = 'https://covid.ourworldindata.org/data/owid-covid-data.csv'
    df = pd.read_csv(url, usecols=['location', 'date', 'total_cases'], parse_dates=['date'])
    df = df[df.location == 'World']
    s = df.set_index('date').total_cases
    return s.rename('Total Cases')
 def get_tickers():
    with selenium.webdriver.Chrome() as driver:
        symbols = {'Bitcoin': 'BTC-USD', 'Gold': 'GC=F', 'Dow Jones': '%5EDJI'}
        for name, symbol in symbols.items():
            yield get_ticker(driver, name, symbol)
 def get_ticker(driver, name, symbol):
    url = f'https://finance.yahoo.com/quote/{symbol}/history/'
    driver.get(url + '?period1=1579651200&period2=9999999999')
    if buttons := driver.find_elements('xpath', '//button[@name="reject"]'):
        buttons[0].click()
    dataframes = pd.read_html(driver.page_source, parse_dates=['Date'])
    s = dataframes[0].set_index('Date').Open
    return s.rename(name)
 def wrangle_data(covid, bitcoin, gold, dow):
    df = pd.concat([bitcoin, gold, dow], axis=1)  # Creates table by joining columns on dates.
    df = df.sort_index().interpolate()            # Sorts rows by date and interpolates NaN-s.
    df = df.loc['2020-02-23':]                    # Discards rows before '2020-02-23'.
    df = df.loc['2020-02-23':'2021-12-20']        # Keeps rows between specified dates.
    df = (df / df.iloc[0]) * 100                  # Calculates percentages relative to day 1.
    df = df.join(covid)                           # Adds column with covid cases.
    return df.sort_values(df.index[-1], axis=1)   # Sorts columns by last day's value.
@ -3494,11 +3503,12 @@ def display_data(df):
        trace = go.Scatter(x=df.index, y=df[col_name], name=col_name, yaxis=yaxis)
        figure.add_trace(trace)
    figure.update_layout(
        width=944,
        height=423,
        yaxis1=dict(title='Total Cases', rangemode='tozero'),
        yaxis2=dict(title='%', rangemode='tozero', overlaying='y', side='right'),
        legend=dict(x=1.08),
        width=944,
        height=423
        colorway=['#EF553B', '#636EFA', '#00CC96', '#FFA152'],
        legend=dict(x=1.08)
    )
    figure.show()
--- a/index.html
+++ b/index.html
@ -55,7 +55,7 @@
 <body>
  <header>
    <aside>December 20, 2024</aside>
    <aside>December 24, 2024</aside>
    <a href="https://gto76.github.io" rel="author">Jure Šorn</a>
  </header>
@ -2052,10 +2052,9 @@ document   = bs4.BeautifulSoup(response.text, <span class="hljs-string">'html.pa
 table      = document.find(<span class="hljs-string">'table'</span>, class_=<span class="hljs-string">'infobox vevent'</span>)
 python_url = table.find(<span class="hljs-string">'th'</span>, text=<span class="hljs-string">'Website'</span>).next_sibling.a[<span class="hljs-string">'href'</span>]
 logo_url   = table.find(<span class="hljs-string">'img'</span>)[<span class="hljs-string">'src'</span>]
 logo       = requests.get(<span class="hljs-string">f'https:<span class="hljs-subst">{logo_url}</span>'</span>).content
 filename   = os.path.basename(logo_url)
 <span class="hljs-keyword">with</span> open(filename, <span class="hljs-string">'wb'</span>) <span class="hljs-keyword">as</span> file:
    file.write(logo)
    file.write(requests.get(<span class="hljs-string">f'https:<span class="hljs-subst">{logo_url}</span>'</span>).content)
 print(<span class="hljs-string">f'<span class="hljs-subst">{python_url}</span>, file://<span class="hljs-subst">{os.path.abspath(filename)}</span>'</span>)
 </code></pre></div></div>
@ -2065,6 +2064,7 @@ print(<span class="hljs-string">f'<span class="hljs-subst">{python_url}</span>,
 &lt;WebDrv&gt; = webdriver.Chrome/Firefox/Safari/Edge()     <span class="hljs-comment"># Opens a browser. Also &lt;WebDrv&gt;.quit().</span>
 &lt;WebDrv&gt;.get(<span class="hljs-string">'&lt;url&gt;'</span>)                                 <span class="hljs-comment"># Also &lt;WebDrv&gt;.implicitly_wait(seconds).</span>
 &lt;str&gt;  = &lt;WebDrv&gt;.page_source                         <span class="hljs-comment"># Returns HTML of fully rendered page.</span>
 &lt;El&gt;   = &lt;WebDrv/El&gt;.find_element(<span class="hljs-string">'css selector'</span>, …)  <span class="hljs-comment"># '&lt;tag&gt;#&lt;id&gt;.&lt;class&gt;[&lt;attr&gt;="&lt;val&gt;"]…'.</span>
 &lt;list&gt; = &lt;WebDrv/El&gt;.find_elements(<span class="hljs-string">'xpath'</span>, …)        <span class="hljs-comment"># '//&lt;tag&gt;[@&lt;attr&gt;="&lt;val&gt;"]…'. See XPath.</span>
 &lt;str&gt;  = &lt;El&gt;.get_attribute(&lt;str&gt;)                    <span class="hljs-comment"># Property if exists. Also &lt;El&gt;.text.</span>
@ -2805,32 +2805,41 @@ px.line(df, x=<span class="hljs-string">'Date'</span>, y=<span class="hljs-strin
 <div><h4 id="displaysamultiaxislinechartoftotalcoronaviruscasesandchangesinpricesofbitcoindowjonesandgold">Displays a multi-axis line chart of total coronavirus cases and changes in prices of Bitcoin, Dow Jones and gold:</h4><p></p><div id="e23ccacc-a456-478b-b467-7282a2165921" class="plotly-graph-div" style="height:287px; width:935px;"></div><pre><code class="python language-python hljs"><span class="hljs-keyword">import</span> pandas <span class="hljs-keyword">as</span> pd, plotly.graph_objects <span class="hljs-keyword">as</span> go
 <div><h4 id="displaysamultiaxislinechartoftotalcoronaviruscasesandchangesinpricesofbitcoindowjonesandgold">Displays a multi-axis line chart of total coronavirus cases and changes in prices of Bitcoin, Dow Jones and gold:</h4><p></p><div id="e23ccacc-a456-478b-b467-7282a2165921" class="plotly-graph-div" style="height:287px; width:935px;"></div><pre><code class="python language-python hljs"><span class="hljs-comment"># $ pip3 install pandas selenium plotly lxml</span>
 <span class="hljs-keyword">import</span> pandas <span class="hljs-keyword">as</span> pd, selenium.webdriver, plotly.graph_objects <span class="hljs-keyword">as</span> go
 <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">main</span><span class="hljs-params">()</span>:</span>
    covid, bitcoin, gold, dow = scrape_data()
    covid, (bitcoin, gold, dow) = get_covid_cases(), get_tickers()
    df = wrangle_data(covid, bitcoin, gold, dow)
    display_data(df)
 <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">scrape_data</span><span class="hljs-params">()</span>:</span>
    <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">get_covid_cases</span><span class="hljs-params">()</span>:</span>
        url = <span class="hljs-string">'https://covid.ourworldindata.org/data/owid-covid-data.csv'</span>
        df = pd.read_csv(url, usecols=[<span class="hljs-string">'location'</span>, <span class="hljs-string">'date'</span>, <span class="hljs-string">'total_cases'</span>])
        df = df[df.location == <span class="hljs-string">'World'</span>]
        <span class="hljs-keyword">return</span> df.set_index(<span class="hljs-string">'date'</span>).total_cases
    <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">get_ticker</span><span class="hljs-params">(symbol)</span>:</span>
        url = (<span class="hljs-string">f'https://query1.finance.yahoo.com/v7/finance/download/<span class="hljs-subst">{symbol}</span>?'</span>
               <span class="hljs-string">'period1=1579651200&amp;period2=9999999999&amp;interval=1d&amp;events=history'</span>)
        df = pd.read_csv(url, usecols=[<span class="hljs-string">'Date'</span>, <span class="hljs-string">'Close'</span>])
        <span class="hljs-keyword">return</span> df.set_index(<span class="hljs-string">'Date'</span>).Close
    out = get_covid_cases(), get_ticker(<span class="hljs-string">'BTC-USD'</span>), get_ticker(<span class="hljs-string">'GC=F'</span>), get_ticker(<span class="hljs-string">'^DJI'</span>)
    names = [<span class="hljs-string">'Total Cases'</span>, <span class="hljs-string">'Bitcoin'</span>, <span class="hljs-string">'Gold'</span>, <span class="hljs-string">'Dow Jones'</span>]
    <span class="hljs-keyword">return</span> map(pd.Series.rename, out, names)
 <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">get_covid_cases</span><span class="hljs-params">()</span>:</span>
    url = <span class="hljs-string">'https://covid.ourworldindata.org/data/owid-covid-data.csv'</span>
    df = pd.read_csv(url, usecols=[<span class="hljs-string">'location'</span>, <span class="hljs-string">'date'</span>, <span class="hljs-string">'total_cases'</span>], parse_dates=[<span class="hljs-string">'date'</span>])
    df = df[df.location == <span class="hljs-string">'World'</span>]
    s = df.set_index(<span class="hljs-string">'date'</span>).total_cases
    <span class="hljs-keyword">return</span> s.rename(<span class="hljs-string">'Total Cases'</span>)
 <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">get_tickers</span><span class="hljs-params">()</span>:</span>
    <span class="hljs-keyword">with</span> selenium.webdriver.Chrome() <span class="hljs-keyword">as</span> driver:
        symbols = {<span class="hljs-string">'Bitcoin'</span>: <span class="hljs-string">'BTC-USD'</span>, <span class="hljs-string">'Gold'</span>: <span class="hljs-string">'GC=F'</span>, <span class="hljs-string">'Dow Jones'</span>: <span class="hljs-string">'%5EDJI'</span>}
        <span class="hljs-keyword">for</span> name, symbol <span class="hljs-keyword">in</span> symbols.items():
            <span class="hljs-keyword">yield</span> get_ticker(driver, name, symbol)
 <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">get_ticker</span><span class="hljs-params">(driver, name, symbol)</span>:</span>
    url = <span class="hljs-string">f'https://finance.yahoo.com/quote/<span class="hljs-subst">{symbol}</span>/history/'</span>
    driver.get(url + <span class="hljs-string">'?period1=1579651200&amp;period2=9999999999'</span>)
    <span class="hljs-keyword">if</span> buttons := driver.find_elements(<span class="hljs-string">'xpath'</span>, <span class="hljs-string">'//button[@name="reject"]'</span>):
        buttons[<span class="hljs-number">0</span>].click()
    dataframes = pd.read_html(driver.page_source, parse_dates=[<span class="hljs-string">'Date'</span>])
    s = dataframes[<span class="hljs-number">0</span>].set_index(<span class="hljs-string">'Date'</span>).Open
    <span class="hljs-keyword">return</span> s.rename(name)
 <span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">wrangle_data</span><span class="hljs-params">(covid, bitcoin, gold, dow)</span>:</span>
    df = pd.concat([bitcoin, gold, dow], axis=<span class="hljs-number">1</span>)  <span class="hljs-comment"># Creates table by joining columns on dates.</span>
    df = df.sort_index().interpolate()            <span class="hljs-comment"># Sorts rows by date and interpolates NaN-s.</span>
    df = df.loc[<span class="hljs-string">'2020-02-23'</span>:]                    <span class="hljs-comment"># Discards rows before '2020-02-23'.</span>
    df = df.loc[<span class="hljs-string">'2020-02-23'</span>:<span class="hljs-string">'2021-12-20'</span>]        <span class="hljs-comment"># Keeps rows between specified dates.</span>
    df = (df / df.iloc[<span class="hljs-number">0</span>]) * <span class="hljs-number">100</span>                  <span class="hljs-comment"># Calculates percentages relative to day 1.</span>
    df = df.join(covid)                           <span class="hljs-comment"># Adds column with covid cases.</span>
    <span class="hljs-keyword">return</span> df.sort_values(df.index[<span class="hljs-number">-1</span>], axis=<span class="hljs-number">1</span>)   <span class="hljs-comment"># Sorts columns by last day's value.</span>
@ -2842,11 +2851,12 @@ px.line(df, x=<span class="hljs-string">'Date'</span>, y=<span class="hljs-strin
        trace = go.Scatter(x=df.index, y=df[col_name], name=col_name, yaxis=yaxis)
        figure.add_trace(trace)
    figure.update_layout(
        width=<span class="hljs-number">944</span>,
        height=<span class="hljs-number">423</span>,
        yaxis1=dict(title=<span class="hljs-string">'Total Cases'</span>, rangemode=<span class="hljs-string">'tozero'</span>),
        yaxis2=dict(title=<span class="hljs-string">'%'</span>, rangemode=<span class="hljs-string">'tozero'</span>, overlaying=<span class="hljs-string">'y'</span>, side=<span class="hljs-string">'right'</span>),
        legend=dict(x=<span class="hljs-number">1.08</span>),
        width=<span class="hljs-number">944</span>,
        height=<span class="hljs-number">423</span>
        colorway=[<span class="hljs-string">'#EF553B'</span>, <span class="hljs-string">'#636EFA'</span>, <span class="hljs-string">'#00CC96'</span>, <span class="hljs-string">'#FFA152'</span>],
        legend=dict(x=<span class="hljs-number">1.08</span>)
    )
    figure.show()
@ -2924,7 +2934,7 @@ $ deactivate                <span class="hljs-comment"># Deactivates the active
  <footer>
    <aside>December 20, 2024</aside>
    <aside>December 24, 2024</aside>
    <a href="https://gto76.github.io" rel="author">Jure Šorn</a>
  </footer>