https://www.youtube.com/watch?v=QLf-pDoJvjQ&list=PLaRYNlxIGoESkuvIdRJNLjdUC4lpF3fM7&index=3&t=0s
================================================================================
Crawling table data
================================================================================
import requests
from bs4 import BeautifulSoup
# Get HTML data from page
r=requests.get("http://lambutan.dothome.co.kr/")
# Bring its contents
c=r.content
# Paser HTML text to HTML format text
soup=BeautifulSoup(c,"html.parser")
================================================================================
# Table structure in HTML
# tbody
# tr
# td
# td
# tr
# tr
# td
# td
# tr
# tbody
================================================================================
# Use find() when you search HTML by "one tag"
# or when you want to get one item from "one tage"
# If there are multiples tags, find() return content of first tag
# all=soup.find('tbody')
# Get all contents inside of tbody
# Get one td from multiple td
# all=soup.find('td')
================================================================================
all=soup.find("tbody")
================================================================================
# After finding "tbody", you need to find "tr"
# You can use soup.find_all()
# It stores tags into list
# [all[0],all[1],...]
================================================================================
all2=all.find_all("tr",{"class":""})
# all2
# [a
,b
,c
]
================================================================================
# Find td
for item in all2:
# Find td tage, class name is professor
professor=item.find("td",{"class":"professor"}).text
lectureName=item.find("td",{"class":"lecture"}).text
orther=item.find("td",{"class":"orther"}).text
grade = item.find("td",{"class": "grade"}).text
evaluation=item.find("td",{"class": "evaluation"}).text
print(professor+"/"+lectureName+"/"+orther+"/"+grade+"/"+evaluation)
# Kim/Python/None/1/1