projects-jenz/event_notification/python/scrape_event.py

112 lines
3.8 KiB
Python

import scrapy
import traceback
from scrapy_settings import EXT_SETTINGS
from pprint import pprint
class unloze_spider(scrapy.Spider):
"""
Main unloze event scraper
"""
custom_settings = EXT_SETTINGS
def __init__(self, item):
self.url = item["url"]
self.item = item
def start_requests(self):
request = scrapy.Request(
url = self.url,
callback = self.parse
)
yield request
def parse(self, response):
"""
Parsing content in the events sections
"""
newest_thread = None
threads = response.xpath("//div[@class='structItem-title']/@uix-href").extract()
for thread in threads:
if "poll" in thread.lower() or "nomination-thread" in thread.lower():
continue
newest_thread = thread
break
if newest_thread is None:
print("no thread found. url: ", response.url)
import sys
sys.exit(1)
request = scrapy.Request(
url = "https://unloze.com" + newest_thread,
callback = self.parse2
)
yield request
def parse2(self, response):
"""
Parsing content on the actual newest event thread
"""
try:
event_title = response.url.rsplit(".", 1)[0].rsplit("/", 1)[1]
event_server = ""
#several event managers do the threads differently in terms of highlighting and marks, they dont use standardization
index = 0
for r in response.xpath("//span[contains(text(),'TL;DR')]/../../../text()").extract():
if "\n" in r or len(r) < 4:
continue
if index < 2:
event_server += r
if index == 2:
event_date = r
if index == 3:
event_time = r
#just skipping the leader part on ze
if index == 4 and '27015' not in event_server:
event_reward = r
if index == 5 and '27015' in event_server:
event_reward = r
index += 1
event_maps = ""
for r in response.xpath("//span[contains(text(),'TL;DR')]/../../../a/text()").extract():
event_maps += f"{r} "
if not index:
tldr_count = 0
for r in response.xpath("//b[contains(text(),'TL;DR')]/../../../span//text()").extract():
if "\n" in r or len(r) < 4:
continue
if "TL;DR" in r:
tldr_count += 1
if tldr_count < 2:
continue
if index == 2 or index == 4:
event_server += r
if index == 7:
event_date = r
if index == 9:
event_time = r
if index == 13:
event_reward = r
index += 1
for r in response.xpath("//b[contains(text(),'TL;DR')]/../../../a//text()").extract():
event_maps += f"{r} "
self.item["event_title"] = event_title
self.item["event_date"] = event_date
self.item["event_time"] = event_time
self.item["event_server"] = event_server
self.item["event_maps"] = event_maps
self.item["event_reward"] = event_reward
self.item["event_url"] = response.url
except Exception:
error_msg = traceback.format_exc()
print("traceback msg: ", error_msg)
print("url: ", response.url)
import sys
sys.exit(1)
#pprint(self.item)
return self.item