bs4 함수

상감자 2018. 5. 16. 12:45

2018. 5. 16. 12:45

find_all( ): 원하는 태그들을 리스트 형식으로

from bs4 import BeautifulSoup

html = """<html><head><title>title name</title></head><body><p>test</p></body></html>"""

soup = BeautifulSoup(html, 'lxml')

html_content = soup.find_all('html')

find_p = html_content[0].find_all('body')

print(soup.find_all('원하는 태그 이름'))

print(soup.find_all(id='원하는 id이름'))

print(soup.find_all('원하는 태그이름', class_='클래스이름'))

print(soup.find_all('원하는 태그이름', '클래스이름'))

print(soup.find_all('원하는 태그이름', text='클래스이름'))

print(soup.find_all()) #모든 값

print(soup.find_all(['태그값1','태그값2']) #태그여러개 불러오기

select( ) : CSS 셀렉터를 활용, 리스트로 반환

from bs4 import BeautifulSoup

html = """<html><head><title>title name</title></head><body><p>test</p></body></html>"""

soup = BeautifulSoup(html, 'lxml')

html_content = soup.find_all('html')

print(soup.select('태그'))

print(soup.select('.클래스이름'))

print(soup.select('#아이디이름'))

print(soup.select('태그 태그.클래스'))

Gamja's Farm