From bf5171e6608afef0571d3b058ca9ad8e19b3331f Mon Sep 17 00:00:00 2001
From: Raphael Roberts <raphael.roberts48@gmail.com>
Date: Sun, 18 Feb 2018 00:54:30 -0600
Subject: [PATCH] initial commit

---
 .gitignore       |  1 +
 __init__.py      |  0
 batch_process.py | 23 +++++++++++++++++
 price_finder.py  | 64 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 88 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 __init__.py
 create mode 100644 batch_process.py
 create mode 100644 price_finder.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ed8ebf5
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+__pycache__
\ No newline at end of file
diff --git a/__init__.py b/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/batch_process.py b/batch_process.py
new file mode 100644
index 0000000..eccf025
--- /dev/null
+++ b/batch_process.py
@@ -0,0 +1,23 @@
+from selenium import webdriver
+from price_finder import price_finder,BS
+def get_prices(links):
+    try:
+        opts = webdriver.chrome.options.Options()
+        opts.add_argument('--headless')
+        driver = webdriver.Chrome(chrome_options = opts,headless= True)
+        results = []
+        for link in links:
+            driver.get(link)
+            results.append(
+                price_finder(
+                    url = link,bs=BS(driver.page_source,'lxml')
+                    )
+                )
+        driver.quit()
+        return results
+    except Exception as excpt:
+        driver.quit()
+        raise excpt
+import saveto
+links  = saveto.load('quad_links')
+products = get_prices(links)
diff --git a/price_finder.py b/price_finder.py
new file mode 100644
index 0000000..e1698aa
--- /dev/null
+++ b/price_finder.py
@@ -0,0 +1,64 @@
+import urllib
+from fake_useragent import UserAgent
+from bs4 import BeautifulSoup as BS
+import re
+import datetime
+
+user_agent = UserAgent().chrome
+re_words = lambda n: re.compile(r"( ?[^ ]+ ?)"+"{0,"+str(n-1)+"}"+r"[^ ]+")
+def get_page(url):
+    page = None
+    while not page:
+        page = urllib.request.Request(url,headers = {"User-Agent":user_agent})
+        page = str(urllib.request.urlopen(page).read())
+        
+    return page
+
+def get_BS(url):
+    return BS(get_page(url),"lxml")
+
+class price_finder:
+    page_funcs = {
+    "www.amazon.com":{
+        "name":lambda page: re.sub(r"( {2,}|\n|\\n)","",page.find("span",id="productTitle").text),
+        "price":lambda page: page.find(name = "span",id = re.compile("priceblock.*")).text
+        },
+    "www.banggood.com":{
+        "name":lambda page: page.find("h1",attrs = {"itemprop":"name"}).text,
+        "price":lambda page: page.find("div",attrs = {"class":"now"}).get("oriprice")
+        },
+    "www.dalprops.com":{
+        "name":lambda page: page.find("h1",attrs = {"class":"product_title"}).text,
+        "price":lambda page: page.find("meta",attrs = {"itemprop":"price"}).get("content")
+        },
+    "www.gearbest.com":{
+        "name":lambda page: page.find("div",attrs = {"class":"goods-info-top"}).find("h1").text,
+        "price":lambda page: page.find(id="unit_price").get("data-orgp")
+        },
+    "hobbyking.com":{
+        "name":lambda page: page.find("h1",attrs={"class":"product-name"}).text,
+        "price":lambda page: page.find("span",id = re.compile(r"product-price.*")).find("span",attrs={"class":"price"}).text
+        }
+    }
+    def __init__(self,url,space_seperated_categories = 7,bs=None):
+        self.url=url
+        self.info_url = urllib.parse.urlparse(url)
+        if self.info_url.netloc not in price_finder.page_funcs.keys():
+            raise NotImplementedError("Not implemented for {}".format(self.info_url.netloc))
+        if bs:
+            self.bs= bs
+        else:
+            self.bs = get_BS(url)
+        self.words = re_words(space_seperated_categories)
+        self.time = datetime.datetime.today()
+        self.info_product = self._get_product_info_()
+
+            
+    def _get_product_info_(self):
+        funcs = price_finder.page_funcs[self.info_url.netloc]
+        return {
+            "product_name":self.words.match(
+                funcs["name"](self.bs)
+                ).group(0),
+            "price":funcs["price"](self.bs).replace("$",""),
+            }