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

Scraping

pull/46/head
Jure Šorn 5 years ago
parent
d1034fceaf
commit
d793f01fae
2 changed files with 30 additions and 24 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 27
      README.md
  2. 27
      index.html

27
README.md
View File

@ -2382,18 +2382,21 @@ Scraping
# $ pip3 install requests beautifulsoup4
import requests
from bs4 import BeautifulSoup
url = 'https://en.wikipedia.org/wiki/Python_(programming_language)'
html = requests.get(url).text
doc = BeautifulSoup(html, 'html.parser')
table = doc.find('table', class_='infobox vevent')
rows = table.find_all('tr')
link = rows[11].find('a')['href']
ver = rows[6].find('div').text.split()[0]
url_i = rows[0].find('img')['src']
image = requests.get(f'https:{url_i}').content
with open('test.png', 'wb') as file:
file.write(image)
print(link, ver)
URL = 'https://en.wikipedia.org/wiki/Python_(programming_language)'
try:
html = requests.get(URL).text
doc = BeautifulSoup(html, 'html.parser')
table = doc.find('table', class_='infobox vevent')
rows = table.find_all('tr')
link = rows[11].find('a')['href']
ver = rows[6].find('div').text.split()[0]
url_i = rows[0].find('img')['src']
image = requests.get(f'https:{url_i}').content
with open('test.png', 'wb') as file:
file.write(image)
print(link, ver)
except requests.exceptions.ConnectionError:
print("You've got problems with connection.")
```

27
index.html
View File

@ -2054,18 +2054,21 @@ logger.&lt;level&gt;(<span class="hljs-string">'A logging message.'</span>)
<div><h2 id="scraping"><a href="#scraping" name="scraping">#</a>Scraping</h2><div><h4 id="scrapespythonsurlversionnumberandlogofromwikipediapage">Scrapes Python's URL, version number and logo from 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
<span class="hljs-keyword">from</span> bs4 <span class="hljs-keyword">import</span> BeautifulSoup
url = <span class="hljs-string">'https://en.wikipedia.org/wiki/Python_(programming_language)'</span>
html = requests.get(url).text
doc = BeautifulSoup(html, <span class="hljs-string">'html.parser'</span>)
table = doc.find(<span class="hljs-string">'table'</span>, class_=<span class="hljs-string">'infobox vevent'</span>)
rows = table.find_all(<span class="hljs-string">'tr'</span>)
link = rows[<span class="hljs-number">11</span>].find(<span class="hljs-string">'a'</span>)[<span class="hljs-string">'href'</span>]
ver = rows[<span class="hljs-number">6</span>].find(<span class="hljs-string">'div'</span>).text.split()[<span class="hljs-number">0</span>]
url_i = rows[<span class="hljs-number">0</span>].find(<span class="hljs-string">'img'</span>)[<span class="hljs-string">'src'</span>]
image = requests.get(<span class="hljs-string">f'https:<span class="hljs-subst">{url_i}</span>'</span>).content
<span class="hljs-keyword">with</span> open(<span class="hljs-string">'test.png'</span>, <span class="hljs-string">'wb'</span>) <span class="hljs-keyword">as</span> file:
file.write(image)
print(link, ver)
URL = <span class="hljs-string">'https://en.wikipedia.org/wiki/Python_(programming_language)'</span>
<span class="hljs-keyword">try</span>:
html = requests.get(URL).text
doc = BeautifulSoup(html, <span class="hljs-string">'html.parser'</span>)
table = doc.find(<span class="hljs-string">'table'</span>, class_=<span class="hljs-string">'infobox vevent'</span>)
rows = table.find_all(<span class="hljs-string">'tr'</span>)
link = rows[<span class="hljs-number">11</span>].find(<span class="hljs-string">'a'</span>)[<span class="hljs-string">'href'</span>]
ver = rows[<span class="hljs-number">6</span>].find(<span class="hljs-string">'div'</span>).text.split()[<span class="hljs-number">0</span>]
url_i = rows[<span class="hljs-number">0</span>].find(<span class="hljs-string">'img'</span>)[<span class="hljs-string">'src'</span>]
image = requests.get(<span class="hljs-string">f'https:<span class="hljs-subst">{url_i}</span>'</span>).content
<span class="hljs-keyword">with</span> open(<span class="hljs-string">'test.png'</span>, <span class="hljs-string">'wb'</span>) <span class="hljs-keyword">as</span> file:
file.write(image)
print(link, ver)
<span class="hljs-keyword">except</span> requests.exceptions.ConnectionError:
print(<span class="hljs-string">"You've got problems with connection."</span>)
</code></pre></div></div>

Write Preview
Loading…
Cancel
Save