From 3ab5fab7a9e13df935775bdb0b1396b8c31be26b Mon Sep 17 00:00:00 2001
From: Anton Sarukhanov <code@ant.sr>
Date: Sun, 27 Nov 2016 09:19:59 -0500
Subject: [PATCH] Convert to web-app
---
app.py | 24 ++++++++++
scrape.py | 105 +++++++++++++++++++++++--------------------
templates/index.html | 39 ++++++++++++++++
3 files changed, 120 insertions(+), 48 deletions(-)
create mode 100644 app.py
create mode 100644 templates/index.html
diff --git a/app.py b/app.py
new file mode 100644
index 0000000..71d1863
--- /dev/null
+++ b/app.py
@@ -0,0 +1,24 @@
+from urllib.parse import urlparse, urljoin
+import re
+from flask import Flask, render_template
+from lxml import html
+import requests
+from scrape import scrape
+
+app = Flask(__name__)
+
+@app.after_request
+def add_header(response):
+ response.cache_control.max_age = 300
+ return response
+
+@app.route("/")
+def index():
+ tournament_name, tournament_details, events = scrape()
+ return render_template('index.html',
+ tournament_name = tournament_name,
+ tournament_details = tournament_details,
+ events = events)
+
+if __name__ == "__main__":
+ app.run()
diff --git a/scrape.py b/scrape.py
index 3df9c17..f9c4f59 100644
--- a/scrape.py
+++ b/scrape.py
@@ -3,52 +3,61 @@ import requests
import re
from urllib.parse import urlparse, urljoin
-results_url = "http://www.escrimeresults.com/cobra/index.htm"
-results = requests.get(results_url)
-results_tree = html.fromstring(results.content)
-try:
- event_urls = results_tree.xpath(
- '//div[@id="schedule"]/table/tr/td/a[text()="View"]/@href')
-except IndexError:
- print("No event schedule found")
- exit()
-tournament_name = results_tree.xpath(
- '//span[@class="tournName"]/text()')[0]
-tournament_details = results_tree.xpath(
- '//span[@class="tournDetails"]/text()')[0]
-print(tournament_name)
-print(tournament_details)
-print("{0} Events\n".format(len(event_urls)))
-events = {}
-for event_url in event_urls:
- if not urlparse(event_url).netloc:
- event_url = urljoin(results_url, event_url)
- event = requests.get(event_url)
- event_tree = html.fromstring(event.content)
- event_details = event_tree.xpath(
+
+def scrape():
+ results_url = "http://www.escrimeresults.com/cobra/index.htm"
+ results = requests.get(results_url)
+ results_tree = html.fromstring(results.content)
+ try:
+ event_urls = results_tree.xpath(
+ '//div[@id="schedule"]/table/tr/td/a[text()="View"]/@href')
+ except IndexError:
+ return "No event schedule found"
+ tournament_name = results_tree.xpath(
+ '//span[@class="tournName"]/text()')[0]
+ tournament_details = results_tree.xpath(
'//span[@class="tournDetails"]/text()')[0]
- print("\n\n{0}".format(event_details))
- if event_tree.xpath('//a[text()="Final Results"]'):
- fencers = event_tree.xpath('//div[@id="finalResults"]/table/tr/td[2]/text()')
- print("Event Closed ({0} fencers)".format(len(fencers)))
- elif event_tree.xpath('//a[text()="Check-In Status"]'):
- checkin_summary = event_tree.xpath(
- 'normalize-space(//div[@class="checkInSummary"]/text())')
- print(checkin_summary)
- fencers = event_tree.xpath('//div[@id="checkIn"]/table/tr/td[2]/text()')
- events[event_details] = []
- prior_events = {}
- for fencer in fencers:
- events[event_details].append(fencer.strip())
- for e in events:
- if e == event_details:
- continue
- if fencer.strip() in events[e]:
- if e in prior_events:
- prior_events[e] += 1
- else:
- prior_events[e] = 1
- break
- for e in prior_events:
- print("{0} Fencers previously fenced in {1}".format(prior_events[e], e))
- # TODO: Tally fencers who have checked in
+ events = []
+ for event_url in event_urls:
+ if not urlparse(event_url).netloc:
+ event_url = urljoin(results_url, event_url)
+ event = requests.get(event_url)
+ event_tree = html.fromstring(event.content)
+ event_details = event_tree.xpath(
+ '//span[@class="tournDetails"]/text()')[0]
+ if event_tree.xpath('//a[text()="Final Results"]'):
+ fencers = event_tree.xpath('//div[@id="finalResults"]/table/tr/td[2]/text()')
+ event_status = "Event Closed ({0} fencers)".format(len(fencers))
+ elif event_tree.xpath('//a[text()="Seeding"]'):
+ fencers = event_tree.xpath('//div[@id="Round1Seeding"]/table/tr/td[2]/text()')
+ event_status = "Event is Ongoing ({0} fencers)".format(len(fencers))
+ elif event_tree.xpath('//a[text()="Check-In Status"]'):
+ event_status = event_tree.xpath(
+ 'normalize-space(//div[@class="checkInSummary"]/text())')
+ fencers = event_tree.xpath('//div[@id="checkIn"]/table/tr/td[2]/text()')
+ try:
+ del this_event
+ except:
+ pass
+ this_event = {
+ 'name': event_details,
+ 'status': event_status,
+ 'fencers': [],
+ 'previously_fenced': {},
+ 'previous_total': 0
+ }
+ for fencer in fencers:
+ this_event['fencers'].append(fencer.strip())
+ for e in events:
+ if e['name'] == event_details:
+ continue
+ if fencer.strip() in e['fencers']:
+ if e['name'] in this_event['previously_fenced']:
+ this_event['previously_fenced'][e['name']] += 1
+ else:
+ this_event['previously_fenced'][e['name']] = 1
+ this_event['previous_total'] += 1
+ break
+ events.append(this_event)
+ # TODO: Tally fencers who have checked in
+ return (tournament_name, tournament_details, events)
diff --git a/templates/index.html b/templates/index.html
new file mode 100644
index 0000000..e5574e5
--- /dev/null
+++ b/templates/index.html
@@ -0,0 +1,39 @@
+<!doctype html>
+<html lang="en">
+<head>
+ <meta charset="utf-8">
+ <title>Armory Dashboard</title>
+ <style>
+ body {
+ font: 14px sans-serif;
+ }
+ section {
+ border-bottom: 2px solid #aaa;
+ }
+ p {
+ margin: .25em 0;
+ }
+ </style>
+</head>
+<body>
+ <h1>{{tournament_name}}</h1>
+ <h2>{{tournament_details}}</h2>
+ <h2>{{events|length}} Events</h2>
+ <hr>
+ {% for e in events %}
+ <section>
+ <a name="{{e['name']}}">
+ <h3><a href="#{{e['name']}}">{{e['name']}}</a></h3>
+ <p>{{e['status']}}</p>
+ {% if e['previously_fenced'] %}
+ <p>{{e['previous_total']}} fencers have previously checked in:</p>
+ <ul>
+ {% for pe in e['previously_fenced'] %}
+ <li>{{pe}} - {{e['previously_fenced'][pe]}} fencers</li>
+ {% endfor %}
+ </ul>
+ {% endif %}
+ </section>
+ {% endfor %}
+</body>
+</html>
--
GitLab