Last active
October 26, 2020 12:34
-
-
Save momoci99/8ea65846297ea020d818a8ff46aedd0e to your computer and use it in GitHub Desktop.
송이 공판현황 데이터 크롤링 + mongodb insert
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 | |
import re | |
from bs4 import BeautifulSoup | |
from pymongo import MongoClient | |
def getNumbers(value): | |
result = re.sub('\s+', '', value) | |
result = result.replace('kg', "").replace(',', "").replace('원', "") | |
return result | |
# Press the green button in the gutter to run the script. | |
if __name__ == '__main__': | |
print('main') | |
my_client = MongoClient("mongodb://localhost:27017/") | |
songi_db = my_client["songi_db"] | |
songi_col = songi_db["songi_collection"] | |
url = 'http://iforest.nfcf.or.kr/forest/user.tdf?a=user.songi.SongiApp&c=1002&sply_date=20201019&pmsh_item_c=01&mc=CYB_FIF_DGS_SNI_02' | |
request_url_format = 'http://iforest.nfcf.or.kr/forest/user.tdf?a=user.songi.SongiApp&c=1002&sply_date=%s&pmsh_item_c=01&mc=CYB_FIF_DGS_SNI_02' | |
req = requests.get(url) | |
# HTML 소스 가져오기 | |
html = req.text | |
# print(html) | |
soup = BeautifulSoup(html, 'html.parser') | |
selects = soup.select( | |
'select > option' | |
) | |
days = [] | |
# days.append() | |
datas = [] | |
for select in selects: | |
new_url = request_url_format % select['value'] | |
req = requests.get(new_url) | |
pag_html = req.text | |
soup = BeautifulSoup(pag_html, 'html.parser') | |
trs = soup.select( | |
'table > tbody tr' | |
) | |
print(select['value']) | |
for tr in trs: | |
# print(tr) | |
# row = [] | |
row = {} | |
row['date'] = select['value'] | |
index = 0 | |
for td in tr.find_all('td'): | |
value = td.get_text().strip() | |
# print(value, index) | |
if index == 0: | |
row['Region'] = value | |
if index == 1: | |
row['Union'] = value | |
if index == 2: | |
spliteds = value.split('\n') | |
row['Yesterday_Count_Sum'] = getNumbers(spliteds[0]) | |
row['Yesterday_Price_Sum'] = getNumbers(spliteds[1]) | |
if index == 3: | |
spliteds = value.split('\n') | |
row['Today_Count_Sum'] = getNumbers(spliteds[0]) | |
row['Today_Price_Sum'] = getNumbers(spliteds[1]) | |
if index == 4: | |
spliteds = value.split('\n') | |
row['Total_Count_Sum'] = getNumbers(spliteds[0]) | |
row['Total_Price_Sum'] = getNumbers(spliteds[1]) | |
if index == 5: | |
spliteds = value.split('\n') | |
row['Fist_Class_Count'] = getNumbers(spliteds[0]) | |
row['Fist_Class_Price'] = getNumbers(spliteds[1]) | |
if index == 6: | |
spliteds = value.split('\n') | |
row['Second_Class_Count'] = getNumbers(spliteds[0]) | |
row['Second_Class_Price'] = getNumbers(spliteds[1]) | |
if index == 7: | |
spliteds = value.split('\n') | |
row['Third_Main_Class_Count'] = getNumbers(spliteds[0]) | |
row['Third_Main_Class_Price'] = getNumbers(spliteds[1]) | |
if index == 8: | |
spliteds = value.split('\n') | |
row['Third_Sub_Class_Count'] = getNumbers(spliteds[0]) | |
row['Third_Sub_Class_Price'] = getNumbers(spliteds[1]) | |
if index == 9: | |
spliteds = value.split('\n') | |
row['Etc_Class_Count'] = getNumbers(spliteds[0]) | |
row['Ect_Class_Price'] = getNumbers(spliteds[1]) | |
if index == 10: | |
spliteds = value.split('\n') | |
row['Mixed_Class_Count'] = getNumbers(spliteds[0]) | |
row['Mixed_Class_Price'] = getNumbers(spliteds[1]) | |
if index == 11: | |
row['Last_Updated'] = value | |
index = index+1 | |
songi_col.insert_one(row) | |
datas.append(row) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment