BeautifulSoup4 Установка
pip install beautifulsoup4
Hurt Hornet
pip install beautifulsoup4#start
from bs4 import BeautifulSoup
import requests
req = requests.get('https://www.slickcharts.com/sp500')
soup = BeautifulSoup(req.text, 'html.parser')mydivs = soup.findAll("div", {"class": "stylelistrow"})#Scrapes Python's URL, version number and logo from its Wikipedia page:
# $ pip3 install requests beautifulsoup4
import requests, bs4, os, sys
WIKI_URL = 'https://en.wikipedia.org/wiki/Python_(programming_language)'
try:
html = requests.get(WIKI_URL).text
document = bs4.BeautifulSoup(html, 'html.parser')
table = document.find('table', class_='infobox vevent')
python_url = table.find('th', text='Website').next_sibling.a['href']
version = table.find('th', text='Stable release').next_sibling.strings.__next__()
logo_url = table.find('img')['src']
logo = requests.get(f'https:{logo_url}').content
filename = os.path.basename(logo_url)
with open(filename, 'wb') as file:
file.write(logo)
print(f'{python_url}, {version}, file://{os.path.abspath(filename)}')
except requests.exceptions.ConnectionError:
print("You've got problems with connection.", file=sys.stderr)from bs4 import BeautifulSoup
with open("index.html") as fp:
soup = BeautifulSoup(fp)
soup = BeautifulSoup("<html>a web page</html>")
import bs4 as bs
import urllib.request
source = urllib.request.urlopen('https://pythonprogramming.net/parsememcparseface/').read()