noham/phpBB-forum-scraper
1
0
Fork 0
mirror of https://github.com/NohamR/phpBB-forum-scraper.git synced 2026-02-22 02:25:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Uploading revised phpBB forum scraping code.

Browse Source
This commit is contained in:
David Ascienzo
2018-08-19 15:47:44 -04:00
commit 01fcfb586b
14 changed files with 324 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
phpBB_scraper/phpBB_scraper/__init__.py Normal file
View File

BIN
phpBB_scraper/phpBB_scraper/__pycache__/__init__.cpython-36.pyc Normal file
View File

Binary file not shown.

BIN
phpBB_scraper/phpBB_scraper/__pycache__/settings.cpython-36.pyc Normal file
View File

Binary file not shown.

14
phpBB_scraper/phpBB_scraper/items.py Normal file
View File

@@ -0,0 +1,14 @@
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class PhpbbScraperItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass

56
phpBB_scraper/phpBB_scraper/middlewares.py Normal file
View File

@@ -0,0 +1,56 @@
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class PhpbbScraperSpiderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the spider middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_spider_input(self, response, spider):
# Called for each response that goes through the spider
# middleware and into the spider.
# Should return None or raise an exception.
return None
def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response.
# Must return an iterable of Request, dict or Item objects.
for i in result:
yield i
def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception.
# Should return either None or an iterable of Response, dict
# or Item objects.
pass
def process_start_requests(self, start_requests, spider):
# Called with the start requests of the spider, and works
# similarly to the process_spider_output() method, except
# that it doesn’t have a response associated.
# Must return only requests (not items).
for r in start_requests:
yield r
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)

11
phpBB_scraper/phpBB_scraper/pipelines.py Normal file
View File

@@ -0,0 +1,11 @@
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
class PhpbbScraperPipeline(object):
def process_item(self, item, spider):
return item

89
phpBB_scraper/phpBB_scraper/settings.py Normal file
View File

@@ -0,0 +1,89 @@
# -*- coding: utf-8 -*-
# Scrapy settings for phpBB_scraper project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'phpBB_scraper'
SPIDER_MODULES = ['phpBB_scraper.spiders']
NEWSPIDER_MODULE = 'phpBB_scraper.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 OPR/45.0.2552.888'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 1.0
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
COOKIES_ENABLED = True
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'phpBB_scraper.middlewares.PhpbbScraperSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'phpBB_scraper.middlewares.MyCustomDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'phpBB_scraper.pipelines.PhpbbScraperPipeline': 300,
#}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

4
phpBB_scraper/phpBB_scraper/spiders/__init__.py Normal file
View File

@@ -0,0 +1,4 @@
# This package will contain the spiders of your Scrapy project
#
# Please refer to the documentation for information on how to create and manage
# your spiders.

BIN
phpBB_scraper/phpBB_scraper/spiders/__pycache__/__init__.cpython-36.pyc Normal file
View File

Binary file not shown.

BIN
phpBB_scraper/phpBB_scraper/spiders/__pycache__/phpBB.cpython-36.pyc Normal file
View File

Binary file not shown.

89
phpBB_scraper/phpBB_scraper/spiders/phpBB.py Normal file
View File

@@ -0,0 +1,89 @@
# -*- coding: utf-8 -*-
import re
import scrapy
from bs4 import BeautifulSoup
from scrapy.http import Request
class PhpbbSpider(scrapy.Spider):
name = 'phpBB'
allowed_domains = ['']
start_urls = ['']
username = ''
password = ''
form_login = False
def parse(self, response):
#LOGIN TO PHPBB BOARD AND CALL AFTER_LOGIN
if self.form_login:
formdata = {'username':self.username,'password':self.password}
form_request = [scrapy.FormRequest.from_response(response,
formdata=formdata,
callback=self.after_login,
dont_click=True)]
return form_request
else:
#REQUEST SUB-FORUM TITLE LINKS
links = response.xpath('//a[@class="forumtitle"]/@href').extract()
for link in links:
yield scrapy.Request(response.urljoin(link),callback=self.parse_topics)
def after_login(self, response):
#CHECK LOGIN SUCCESS BEFORE MAKING REQUESTS
if b'authentication failed' in response.body:
self.logger.error('Login failed.')
return
else:
#REQUEST SUB-FORUM TITLE LINKS
links = response.xpath('//a[@class="forumtitle"]/@href').extract()
for link in links:
yield scrapy.Request(response.urljoin(link),callback=self.parse_topics)
def parse_topics(self, response):
#REQUEST TOPIC TITLE LINKS
links = response.xpath('//a[@class="topictitle"]/@href').extract()
for link in links:
yield scrapy.Request(response.urljoin(link),callback=self.parse_posts)
#IF NEXT PAGE EXISTS, FOLLOW
Next = response.xpath("//li[@class='next']//a[@rel='next']/@href").extract_first()
if Next:
yield scrapy.Request(response.urljoin(Next),callback=self.parse_topics)
def clean_quote(self, string):
#CLEAN HTML TAGS FROM POST TEXT, MARK QUOTES
soup = BeautifulSoup(string,'lxml')
blockQuotes = soup.find_all('blockquote')
for i, quote in enumerate(blockQuotes):
blockQuotes[i] = '<quote-%s>=' + str(i) + quote.get_text()
text = ''.join(blockQuotes)
return text
def clean_text(self, string):
#CLEAN HTML TAGS FROM POST TEXT, MARK REPLIES TO QUOTES
tags = ['blockquote']
soup = BeautifulSoup(string,'lxml')
for tag in tags:
for i, item in enumerate(soup.find_all(tag)):
item.replaceWith('<reply-%s>=' + str(i))
text = re.sub(' +',' ',soup.get_text())
return text
def parse_posts(self, response):
#COLLECT FORUM POST DATA
usernames = response.xpath('//p[@class="author"]//a[@class="username"]//text()').extract()
postCounts = response.xpath('//dd[@class="profile-posts"]//a/text()').extract()
postTimes = response.xpath('//p[@class="author"]/text()').extract()
postTexts = response.xpath('//div[@class="postbody"]//div[@class="content"]').extract()
postQuotes = [self.clean_quote(s) for s in postTexts]
postTexts = [self.clean_text(s) for s in postTexts]
#YIELD POST DATA
for i in range(len(usernames)):
yield {'User':usernames[i],'Count':postCounts[i],
'Time':postTimes[i],'Post Text':postTexts[i],'Quote Text':postQuotes[i]}
#CLICK THROUGH NEXT PAGE
Next = response.xpath("//li[@class='next']//a[@rel='next']/@href").extract_first()
if Next:
yield scrapy.Request(response.urljoin(Next),callback=self.parse_posts)

11
phpBB_scraper/scrapy.cfg Normal file
View File

@@ -0,0 +1,11 @@
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = phpBB_scraper.settings
[deploy]
#url = http://localhost:6800/
project = phpBB_scraper