Text-Summarizer / src /utils.py
Gladiator's picture
add url support for summarization
fe021fb
raw
history blame
1.81 kB
import re
import requests
from bs4 import BeautifulSoup
emoji_pattern = re.compile(
"["
u"\U0001F600-\U0001F64F" # emoticons
u"\U0001F300-\U0001F5FF" # symbols & pictographs
u"\U0001F680-\U0001F6FF" # transport & map symbols
u"\U0001F1E0-\U0001F1FF" # flags (iOS)
u"\U00002702-\U000027B0"
u"\U000024C2-\U0001F251"
"]+",
flags=re.UNICODE,
)
def clean_text(x):
# x = x.lower() # lowercase
x = x.encode("ascii", "ignore").decode() # unicode
x = re.sub(r"https*\S+", " ", x) # url
x = re.sub(r"@\S+", " ", x) # mentions
x = re.sub(r"#\S+", " ", x) # hastags
x = x.replace("'", "") # remove ticks
# x = re.sub("[%s]" % re.escape(string.punctuation), " ", x) # punctuation
# x = re.sub(r"\w*\d+\w*", "", x) # numbers
x = re.sub(r"\s{2,}", " ", x) # over spaces
x = emoji_pattern.sub(r"", x) # emojis
x = re.sub("[^A-Za-z0-9]+", " ", x) # special charachters
return x
def fetch_article_text(url: str):
r = requests.get(url)
soup = BeautifulSoup(r.text, "html.parser")
results = soup.find_all(["h1", "p"])
text = [result.text for result in results]
ARTICLE = " ".join(text)
sentences = ARTICLE.split("<eos>")
current_chunk = 0
chunks = []
for sentence in sentences:
if len(chunks) == current_chunk + 1:
if len(chunks[current_chunk]) + len(sentence.split(" ")) <= 500:
chunks[current_chunk].extend(sentence.split(" "))
else:
current_chunk += 1
chunks.append(sentence.split(" "))
else:
print(current_chunk)
chunks.append(sentence.split(" "))
for chunk_id in range(len(chunks)):
chunks[chunk_id] = " ".join(chunks[chunk_id])
return ARTICLE, chunks