jerielizabeth

jerielizabeth

import nltk

with open('sample.txt', 'r') as f:
    sample = f.read()
     
sentences = nltk.sent_tokenize(sample)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
chunked_sentences = nltk.batch_ne_chunk(tagged_sentences, binary=True)

jerielizabeth

.block {
  width: 30%;
  float:left;
  background-color: gray;
  margin: 10px;
}

.navigation {
  background-color:green;
  width: 33%;

jerielizabeth

<section class="block">
  <h2>some header </h2>
  <p>Some text</p>
  <a href="#">Read More</a>
</section>
  
<section class="block">
  <h2>another header </h2>
  <p>Some text</p>
  <a href="#">Read More</a>

jerielizabeth

from bs4 import BeautifulSoup
import csv

#open the html file and create a soup object
soup = BeautifulSoup(open("43rd-congress.html"))

#get rid of the final link that is outside the table
final_link = soup.p.a
final_link.decompose()

jerielizabeth

jerielizabeth

from bs4 import BeautifulSoup
import csv

soup = BeautifulSoup (open("43rd-congress.html"))

final_link = soup.p.a
final_link.decompose()

links = soup.find_all('a')
for link in links:	

jerielizabeth

from bs4 import BeautifulSoup

soup = BeautifulSoup (open("43rd-congress.html"))

links = soup.find_all('a')

for link in links:
	print link

jerielizabeth

from bs4 import BeautifulSoup

soup = BeautifulSoup (open("43rd-congress.html"))

print(soup.get_text())

jerielizabeth

from bs4 import BeautifulSoup

soup = BeautifulSoup (open("43rd-congress.html"))

final_link = soup.p.a
final_link.decompose()

people = soup.find_all('a')