Created
April 1, 2018 03:44
-
-
Save jennyonjourney/659bd1152fe516bc16c3d63d12c26dd9 to your computer and use it in GitHub Desktop.
Python - Web crawling (csv파일로 저장하기)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from lxml.html import parse | |
from io import StringIO | |
def rowData(rr, kind): | |
cols = rr.findall('.//'+kind) | |
res = [vv.text_content().replace("\t","").replace("\n","") for vv in cols] | |
return res[:-1] | |
def rowWrite(rr): | |
res ='' | |
cnt =0 | |
for i in rr: | |
cnt += 1 | |
res+=i | |
if len(rr)>cnt: | |
res+=',' | |
res +='\n' | |
return res | |
f=open('../fff/webData.csv','w', encoding='utf-8') | |
for i in range(1,30): | |
url='http://finance.naver.com/sise/sise_market_sum.nhn?page=%d'%i | |
text = requests.get(url) | |
ppp = parse(StringIO(text.text)) | |
doc = ppp.getroot() | |
tables = doc.findall('.//table') | |
#print(tables) ###표들 | |
tt = tables[1] ###표1번째 | |
rows = tt.findall('.//tr') ###줄들 | |
for row in rows[2:]: | |
rr = rowData(row, 'td'); | |
if len(rr)>2: | |
print(rr) | |
f.write(rowWrite(rr)) | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment