데이터 분석/데이터 수집
urllib request soup
star빛
2021. 4. 18. 22:00
# To add a new cell, type '# %%'
# To add a new markdown cell, type '# %% [markdown]'
# %%
# 2021-04-18
# %%
from urllib import request
w = request.urlopen('https://www.weatheri.co.kr/forecast/forecast01.php?mNum=1&sNum=1')
w.read().decode('utf-8')[:100]
# %%
# requests 모듈 설치
# !pip install requests
# %%
# !chcp 65001
# %%
import requests
r = requests.get('https://www.weatheri.co.kr/forecast/forecast01.php?mNum=1&sNum=1')
print( r.status_code )
r.text[:100]
# %%
from bs4 import BeautifulSoup
# %%
html_doc = """<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and
their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a>
and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>"""
# %%
soup = BeautifulSoup(html_doc, 'html.parser')
# %%
soup.prettify()
# %%
type(soup.title), soup.title
# %%
soup.title.name, soup.title.string
# %%
soup.title.parent.name
# %%
soup.p
# %%
soup.p['class']
# %%
soup.a
# %%
soup.find_all('a')
# %%
soup.find(id="link3")
# %%
for link in soup.find_all('a'):
print(link.get('href'))
print(link['href'])
# %%
soup.get_text()