From 455c7222b52e7c3aa7f4eb4b03e9b6f0a99adaef Mon Sep 17 00:00:00 2001
From: NissesSenap <edvin.norling@gmail.com>
Date: Fri, 5 Oct 2018 22:23:49 +0200
Subject: [PATCH] Use self.loop.create_task

Creating a class and make the eventloop avliable with self.
Call it in the get_title_range function.
---
 .../web_scraping/async_scrape/program.py      | 72 ++++++++-----------
 1 file changed, 31 insertions(+), 41 deletions(-)

diff --git a/src/04-asyncio/web_scraping/async_scrape/program.py b/src/04-asyncio/web_scraping/async_scrape/program.py
index 275fccd..ef04965 100644
--- a/src/04-asyncio/web_scraping/async_scrape/program.py
+++ b/src/04-asyncio/web_scraping/async_scrape/program.py
@@ -1,58 +1,48 @@
-import asyncio
-
 import aiohttp
 import bs4
 from colorama import Fore
+import asyncio
 
 
-async def get_html(episode_number: int) -> str:
-    print(Fore.YELLOW + f"Getting HTML for episode {episode_number}", flush=True)
-
-    url = f'https://talkpython.fm/{episode_number}'
-
-    async with aiohttp.ClientSession() as session:
-        async with session.get(url) as resp:
-            resp.raise_for_status()
-
-            return await resp.text()
-
-
-def get_title(html: str, episode_number: int) -> str:
-    print(Fore.CYAN + f"Getting TITLE for episode {episode_number}", flush=True)
-    soup = bs4.BeautifulSoup(html, 'html.parser')
-    header = soup.select_one('h1')
-    if not header:
-        return "MISSING"
+class Scraper:
 
-    return header.text.strip()
+    def __init__(self):
+        self.loop = asyncio.get_event_loop()
+        self.loop.run_until_complete(self.get_title_range())
 
+    async def get_html(self, episode_number: int) -> str:
+        print(Fore.YELLOW + f"Getting HTML for episode {episode_number}", flush=True)
 
-def main():
-    loop = asyncio.get_event_loop()
-    loop.run_until_complete(get_title_range())
-    print("Done.")
+        url = f'https://talkpython.fm/{episode_number}'
+        # resp = requests.get(url)
+        async with aiohttp.ClientSession() as session:
+            async with session.get(url) as resp:
+                resp.raise_for_status()
 
+                return await resp.text()
 
-async def get_title_range_old_version():
-    # Please keep this range pretty small to not DDoS my site. ;)
-    for n in range(150, 160):
-        html = await get_html(n)
-        title = get_title(html, n)
-        print(Fore.WHITE + f"Title found: {title}", flush=True)
+    def get_title(self, html: str, episode_number: int) -> str:
+        print(Fore.CYAN + f"Getting TITLE for episode {episode_number}", flush=True)
+        soup = bs4.BeautifulSoup(html, 'html.parser')
+        header = soup.select_one('h1')
+        if not header:
+            return "MISSING"
 
+        return header.text.strip()
 
-async def get_title_range():
-    # Please keep this range pretty small to not DDoS my site. ;)
+    async def get_title_range(self):
+        # Please keep this range pretty small to not DDoS my site. ;)
 
-    tasks = []
-    for n in range(150, 160):
-        tasks.append((n, asyncio.create_task(get_html(n))))
+        tasks = []
+        for n in range(150, 160):
+            tasks.append((n, self.loop.create_task(self.get_html(n))))
 
-    for n, t in tasks:
-        html = await t
-        title = get_title(html, n)
-        print(Fore.WHITE + f"Title found: {title}", flush=True)
+        for n, t in tasks:
+            html = await t
+            title = self.get_title(html, n)
+            print(Fore.WHITE + f"Title found: {title}", flush=True)
 
 
 if __name__ == '__main__':
-    main()
+    Scraper()
+