python webscrapping

webscrapping_01_simple.py

################################################################################################
#	name:	webscrapping_01_simple.py
#	desc:	webscraping using beautifulsoup 
#	date:	2018-11-08
#	Author:	conquistadorjd
################################################################################################
from bs4 import BeautifulSoup
import requests

url = 'https://en.wikipedia.org/wiki/List_of_programming_languages'
r  = requests.get(url)

data = r.text

soup = BeautifulSoup(data, features = "lxml")

header = soup.find('h1')
print('header : ', header)
print('header Text: ', header.text)

webscrapping_02.py

################################################################################################
#	name:	webscrapping_02.py
#	desc:	webscraping using beautifulsoup 
#	date:	2018-11-08
#	Author:	conquistadorjd
################################################################################################
from bs4 import BeautifulSoup
import requests

url = 'https://en.wikipedia.org/wiki/List_of_programming_languages'
r  = requests.get(url)

data = r.text

soup = BeautifulSoup(data, features = "lxml")

# to fetch specific tag
header = soup.find('h1')
print('header : ', header)
print('header Text: ', header.text)

# to fetch tag having specific attribute
var1 = soup.find(attrs={"class" : "navbox-title"})
print("var1 : ", var1)
print("var1 : ", var1.text)

# to fetch all <li> tas
for link in soup.find_all('li'):
    print(link.text)