richard
/
python-cheatsheet
mirror of https://github.com/gto76/python-cheatsheet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

Plot, Scraping

main
Jure Šorn 3 weeks ago
parent
9c992fef98
commit
367ec2f788
2 changed files with 24 additions and 24 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 22
      README.md
  2. 26
      index.html

22
README.md
View File

@ -2405,10 +2405,10 @@ Plot
import matplotlib.pyplot as plt
plt.plot/bar/scatter(x_data, y_data [, label=<str>]) # Also plt.plot(y_data).
plt.legend() # Adds a legend.
plt.title/xlabel/ylabel(<str>) # Adds a title or label.
plt.legend() # Adds a legend of labels.
plt.title/xlabel/ylabel(<str>) # Adds title or axis label.
plt.show() # Also plt.savefig(<path>).
plt.clf() # Clears the plot.
plt.clf() # Clears the plot (figure).
```
@ -2491,16 +2491,16 @@ Scraping
# $ pip3 install requests beautifulsoup4
import requests, bs4, os
url = 'https://en.wikipedia.org/wiki/Python_(programming_language)'
response = requests.get(url, headers={'User-Agent': 'cpc-bot'})
document = bs4.BeautifulSoup(response.text, 'html.parser')
table = document.find('table', class_='infobox vevent')
get = lambda url: requests.get(url, headers={'User-Agent': 'cpc-bot'})
response = get('https://en.wikipedia.org/wiki/Python_(programming_language)')
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']
filename = os.path.basename(logo_url)
logo_url = table.find('img')['src']
filename = os.path.basename(logo_url)
with open(filename, 'wb') as file:
file.write(requests.get(f'https:{logo_url}').content)
print(f'{python_url}, file://{os.path.abspath(filename)}')
file.write(get(f'https:{logo_url}').content)
print(f'URL: {python_url}, logo: file://{os.path.abspath(filename)}')
```
### Selenium

26
index.html
View File

@ -56,7 +56,7 @@
<body>
<header>
<aside>September 7, 2025</aside>
<aside>September 8, 2025</aside>
<a href="https://gto76.github.io" rel="author">Jure Šorn</a>
</header>
@ -1983,10 +1983,10 @@ Processing: 100%|████████████████████| 3
<span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt
plt.plot/bar/scatter(x_data, y_data [, label=&lt;str&gt;]) <span class="hljs-comment"># Also plt.plot(y_data).</span>
plt.legend() <span class="hljs-comment"># Adds a legend.</span>
plt.title/xlabel/ylabel(&lt;str&gt;) <span class="hljs-comment"># Adds a title or label.</span>
plt.legend() <span class="hljs-comment"># Adds a legend of labels.</span>
plt.title/xlabel/ylabel(&lt;str&gt;) <span class="hljs-comment"># Adds title or axis label.</span>
plt.show() <span class="hljs-comment"># Also plt.savefig(&lt;path&gt;).</span>
plt.clf() <span class="hljs-comment"># Clears the plot.</span>
plt.clf() <span class="hljs-comment"># Clears the plot (figure).</span>
</code></pre></div>
<div><h2 id="table"><a href="#table" name="table">#</a>Table</h2><div><h4 id="printsacsvspreadsheettotheconsole">Prints a CSV spreadsheet to the console:</h4><pre><code class="python language-python hljs"><span class="hljs-comment"># $ pip3 install tabulate</span>
@ -2051,16 +2051,16 @@ window.close()
<div><h2 id="scraping"><a href="#scraping" name="scraping">#</a>Scraping</h2><div><h4 id="scrapespythonsurlandlogofromitswikipediapage">Scrapes Python's URL and logo from its Wikipedia page:</h4><pre><code class="python language-python hljs"><span class="hljs-comment"># $ pip3 install requests beautifulsoup4</span>
<span class="hljs-keyword">import</span> requests, bs4, os
url = <span class="hljs-string">'https://en.wikipedia.org/wiki/Python_(programming_language)'</span>
response = requests.get(url, headers={<span class="hljs-string">'User-Agent'</span>: <span class="hljs-string">'cpc-bot'</span>})
document = bs4.BeautifulSoup(response.text, <span class="hljs-string">'html.parser'</span>)
table = document.find(<span class="hljs-string">'table'</span>, class_=<span class="hljs-string">'infobox vevent'</span>)
get = <span class="hljs-keyword">lambda</span> url: requests.get(url, headers={<span class="hljs-string">'User-Agent'</span>: <span class="hljs-string">'cpc-bot'</span>})
response = get(<span class="hljs-string">'https://en.wikipedia.org/wiki/Python_(programming_language)'</span>)
document = bs4.BeautifulSoup(response.text, <span class="hljs-string">'html.parser'</span>)
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>]
filename = os.path.basename(logo_url)
logo_url = table.find(<span class="hljs-string">'img'</span>)[<span class="hljs-string">'src'</span>]
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(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>)
file.write(get(<span class="hljs-string">f'https:<span class="hljs-subst">{logo_url}</span>'</span>).content)
print(<span class="hljs-string">f'URL: <span class="hljs-subst">{python_url}</span>, logo: file://<span class="hljs-subst">{os.path.abspath(filename)}</span>'</span>)
</code></pre></div></div>
@ -2933,7 +2933,7 @@ $ deactivate <span class="hljs-comment"># Deactivates the active
<footer>
<aside>September 7, 2025</aside>
<aside>September 8, 2025</aside>
<a href="https://gto76.github.io" rel="author">Jure Šorn</a>
</footer>

Write Preview
Loading…
Cancel
Save