[網路爬蟲] Python將網頁資料擷取

範例：擷取新北市觀光工廠資料

import requests as rq
from xml.etree import ElementTree
import pandas as pd

url='https://data.ntpc.gov.tw/od/data/api/57EB9B00-979C-44BB-A4EE-CC55BDF1488A?$format=xml'
r=rq.request('GET',url)

tree=ElementTree.fromstring(r.content)
list_data=[]
for i in tree.iter('row'):
    single_record=[]
    for j in i.iter():
        if j.tag=='title' or j.tag=='features' or j.tag=='tel' or j.tag=='address':
            single_record.append(j.text)
    list_data.append(single_record)

df=pd.DataFrame(list_data,columns=['名稱','特色','電話','地址'])
df.index+=1
print(df)