Beautifulsoup XML 분석

Beautifulsoup을 이용해 XML을 분석할 수 있다.

from bs4 import BeautifulSoup
import urllib.request as req
import os.path
 
url = "http://www.weather.go.kr/weather/forecast/mid-term-rss3.jsp?stnId=108"
# 기상청 날씨누리 전국 중기예보 RSS
filename = "forecast.xml"
 
if not os.path.exists(filename):
    #req.urlretrieve(url, savename)
    # Legacy interface. It might become deprecated at some point in the future.
    with req.urlopen(url) as contents:
        xml = contents.read().decode("utf-8")
        # If the end of the file has been reached, read() will return an empty string ('').
        #print(xml)
        with open(filename, mode="wt") as f:
            f.write(xml)
 
with open(filename, mode="rt") as f:
    xml = f.read()
    soup = BeautifulSoup(xml, "html.parser")
    # html.parser는 모든 태그를 소문자로 바꾼다.
    #print(soup)
 
    print("[", soup.find("title").string, "]")
    print(soup.find("wf").string, "\n")
 
    # 날씨에 따른 지역 분류
    info = {}    # empty dicionary
    for location in soup.find_all("location"):
        name = location.find("city").string
        weather = location.find("wf").string
        if not (weather in info):
            info[weather] = []    # empty list. dictionary는 list를 value로 가질 수 있다.
        info[weather].append(name)
 
    for weather in info.keys():    # Return a new view of the dictionary’s keys.
        print("■", weather)
        for name in info[weather]:
            print("|-", name)