# 網路爬蟲實作

###### tags: `光復高中`, `光啟高中`, `網路爬蟲`, `Python`

## Step 1: 課程講義

* 光復高中：https://github.com/ycwang812/KFSH
* 光啟高中：https://github.com/ycwang812/PHSH

## Step 2: 線上使用環境

Google Colaboratory - https://colab.research.google.com/notebooks/

## Step 3: 建立 Notebook

File > New Notebook > 名稱為 Starbuzz.ipynb

## Step 4: 取得咖啡豆網頁資訊

import urllib.request

page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
text = page.read().decode("utf8")

print(text)

## Step 5: 找出價格

import urllib.request

page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
text = page.read().decode("utf8")
price = text[234:238]

print(price)

## Step 6: 動態找價格

import urllib.request

page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
text = page.read().decode("utf8")

where = text.find(">$")

start_of_price = where + 2
end_of_price = start_of_price + 4

price = text[start_of_price:end_of_price]

print(price)

## Step 7: 找到最低價格 (會錯!)

import urllib.request

price = 99.99

while price > 5.9:
  page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
  text = page.read().decode("utf8")

  where = text.find(">$")

  start_of_price = where + 2
  end_of_price = start_of_price + 4

  price = text[start_of_price:end_of_price]
  
print("Buy!")

## Step 8: 轉換變數型別

import urllib.request

price = 99.99

while price > 5.9:
  page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
  text = page.read().decode("utf8")

  where = text.find(">$")

  start_of_price = where + 2
  end_of_price = start_of_price + 4

  price = float(text[start_of_price:end_of_price])
  
print("Buy!")

## Step 9: 減少伺服器負載

import urllib.request
import time

price = 99.99

while price > 5.9:
  time.sleep(900)
  
  page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
  text = page.read().decode("utf8")

  where = text.find(">$")

  start_of_price = where + 2
  end_of_price = start_of_price + 4

  price = float(text[start_of_price:end_of_price])
  
print("Buy!")

## Step 10: 減少程式重複性

import urllib.request

def get_price():
  page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
  text = page.read().decode("utf8")

  where = text.find(">$")

  start_of_price = where + 2
  end_of_price = start_of_price + 4

  print(text[start_of_price:end_of_price])

get_price()

## Step 11: 函式回傳值

import urllib.request

def get_price():
  page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
  text = page.read().decode("utf8")

  where = text.find(">$")

  start_of_price = where + 2
  end_of_price = start_of_price + 4

  return(text[start_of_price:end_of_price])

price = get_price()

print(price)

## Step 12: 增加判斷式

import urllib.request
import time

def get_price():
  page = urllib.request.urlopen("http://beans-r-us.appspot.com/prices.html")
  text = page.read().decode("utf8")

  where = text.find(">$")

  start_of_price = where + 2
  end_of_price = start_of_price + 4

  return(float(text[start_of_price:end_of_price]))

price_now = input("Do you want to see the price now (Y/N)?")

if price_now == "Y":
  print(get_price())
else:
  price = 99.99

  while price > 5.9:
    time.sleep(900)

    price = get_price
  
  print("Buy!")