Created
February 27, 2016 00:07
-
-
Save VitamintK/348f4fbe190bdf47eeae to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding: utf-8 | |
# In[54]: | |
from bs4 import BeautifulSoup | |
# In[55]: | |
import requests | |
# In[56]: | |
wikipedia = requests.get("https://en.wikipedia.org/wiki/University_of_California,_Irvine") | |
# In[57]: | |
wikipedia | |
# In[62]: | |
soup = BeautifulSoup(wikipedia.text) | |
# In[65]: | |
print(soup.prettify()) | |
# In[68]: | |
import re | |
# In[75]: | |
url = "https://en.wikipedia.org/wiki/Category:University_of_California,_Irvine_alumni" | |
# In[77]: | |
soup2 = BeautifulSoup(requests.get(url).text) | |
# In[81]: | |
content = soup2.find(class_="mw-content-ltr") | |
content | |
# In[90]: | |
links = [tag for tag in content.find_all("a") if (':' not in tag['href'] if "href" in tag.attrs else False)] | |
# In[95]: | |
from urllib.parse import urljoin | |
# In[97]: | |
links = [urljoin(url, link['href']) for link in links] | |
# In[99]: | |
len(links) | |
# In[ ]: | |
# In[100]: | |
import time | |
# In[103]: | |
for link in links: | |
page = requests.get(link) | |
soup = BeautifulSoup(page) | |
soup | |
time.sleep(1) | |
# In[ ]: | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment