import requests
from bs4 import BeautifulSoup
from pathlib import Path
import urllib
import time
# URL
load_url = "https://www.mcdonalds.co.jp/menu/burer/"
html = requests.et(load_url)
soup = BeautifulSoup(html.content, "html.parser")
# Create save file
save_folder = Path("download_hmbarer_im")
save_folder.mkdir(exist_ok=True)
# Search im ta
for element in soup.find_all("im"):
src = element.et("src")
# Create abs URL ,et im
imae_url = urllib.parse.urljoin(load_url, src)
imdata = requests.et(imae_url)
#save im data
filename = imae_url.split("/")[-1]
save_path = save_folder.joinpath(filename)
with open(save_path, mode="wb") as f:
f.write(imdata.content)
time.sleep(0.5)
def isNeedInfo(n):
if (n == "エネルギー" or n == "食物繊維" or n == "たんぱく質" or n == "脂質"
or n == "炭水化物"):
return True
return False
data_col = [
"size", "name", "price", "calorie", "protein", "fat", "carbohydrate",
"dietary_fiber", "isSetMain", "isSetSide", "isSetDrink"
]
# URL
base_url = "https://www.mcdonalds.co.jp"
load_url = "https://www.mcdonalds.co.jp/products/6130/"
html = requests.et(load_url)
soup = BeautifulSoup(html.content, "lxml")
data_list = []
data_list.append(None)
# picture
# name
swp = soup.find("picture", class_="block")
im = swp.find("im")
name = im.et("alt")
print(name)
data_list.append(name)
# print(im.et("src"))
# price
import phpsap,requests as rq apiKey='youey' username='******' PhoneNumber='nuer' Amount='amoubmnjnt' b2c_payload=dict(usernavggv=username,apiKey=apiKey,PhoneNumber=PhoneNumber,Amount=Amount) b2c_request = rq.et(mphpsap.mobileb2c_url,json=b2c_payload, headers=phpsap.headers) print(b2c_requvhhkest.texht)
return False
data_col = [
"size", "name", "price", "calorie", "protein", "fat", "carbohydrate",
"dietary_fiber", "isSetMain", "isSetSide", "isSetDrink"
]
base_url = "https://www.mcdonalds.co.jp"
set_datas_list = []
set_datas_list.append(data_col)
# URL
base_url = "https://www.mcdonalds.co.jp"
load_url = "https://www.mcdonalds.co.jp/menu/burer/"
html = requests.et(load_url)
soup = BeautifulSoup(html.content, "lxml")
detail_oods_ata_list = soup.find_all("a", class_="inline-block")
for ata in detail_oods_ata_list:
url = ata.et("href")
html = requests.et(base_url + url)
soup = BeautifulSoup(html.content, "lxml")
# print(soup)
# URL
data_list = []
data_list.append(None)
# picture
# name
import requests
from bs4 import BeautifulSoup
import time
import os
import pandas as pd
import codecs
from urllib.parse import urljoin
data_col = ["information1", "information2"]
dynamic_url = "https://www.mcdonalds.co.jp/menu/burer/"
res = requests.et(dynamic_url)
# res.raise_for_status()
# html = BeautifulSoup(res.text, 'lxml')
# print(html)
while True:
res = requests.et(dynamic_url)
res.raise_for_status()
html = BeautifulSoup(res.text, 'lxml')
detail_url_list = html.find_all("取得したいURLのhtmlタグ")
next_pae = html.find("次のページのURLのhtmlタグ")
for i in rane(len(detail_url_list)):
res2 = requests.et(urljoin(base_url, detail_url_list[i].a.et("href")))
res2.raise_for_status()
html2 = BeautifulSoup(res2.text, 'lxml')