updated to reflect TPB site changes and various bug fixes

master
Master 2020-08-02 23:37:05 -04:00
parent 3725629ada
commit 3cff05035b
6 changed files with 39 additions and 16 deletions

View File

@ -69,7 +69,7 @@ class Scallywag:
self.searcher = searcher.Scraper( self.config )
results = self.searcher.get_results( search_terms )
self.status("{0} results found.".format( len(results) ) )
for result in results:
yield result

View File

@ -1,2 +1,2 @@
[list_source]
piratebay_proxy_list = thepiratebay-proxylist.se
piratebay_proxy_list = https://piratebayproxy.info/

View File

@ -9,7 +9,7 @@ class Scraper:
self.config = config
def get_proxies(self):
fetch_results = self.client.get( "https://" + self.config.proxylist_url )
fetch_results = self.client.get( self.config.proxylist_url )
proxy_list = self.Parser.scrape( "proxy_list", fetch_results.content )
return proxy_list
@ -24,7 +24,9 @@ class Scraper:
@staticmethod
def proxy_list( text ):
proxyTable = html.fromstring( text )
proxyTable_xpath = proxyTable.xpath( '//table[@class="proxies"]/tbody/tr/@data-domain' )
proxyTable_xpath = proxyTable.xpath('//body[@id="mainPage"]/div[@class="container"]/div[@id="content"]/table[@id="searchResult"]/tr/td[@class="site"]/a/text()')
for proxy in proxyTable_xpath:
print("Available Proxy: {0}".format( proxy ) )
return proxyTable_xpath
class SessionError( Exception ):

View File

@ -3,6 +3,7 @@ from lxml import html
import urllib
import re
import json
import sys
class Result:
def __init__(self, title, seeders, leechers, size, author, url):
@ -32,24 +33,30 @@ class Scraper:
def craft_url(self, protocol, proxy, search_terms):
# https://pirate.blue/s/?q=Raising+Arizona&category=0&page=0&orderby=99
f = { 'q': search_terms, 'category': 0, 'page': 0, 'orderby': 99 }
url = str.format( "{0}://{1}/s/?{2}", protocol, proxy, urllib.parse.urlencode(f) )
f = { 'q': search_terms, 'page': 0, 'orderby': 99 }
# https://thepiratebay0.org/s/?page=0&orderby=0&q=inuyasha
# https://thepiratebay0.org/s/?page=0&orderby=0&q=inuyasha
url = "{0}://{1}/s/?{2}".format( protocol, proxy, urllib.parse.urlencode(f) )
print(url)
return url
def get_results(self, search_terms):
url = self.craft_url( "https", self.config.proxy, search_terms )
try:
fetch_results = self.client.get( url )
except requests.exceptions.RequestException as e:
print( e, file=sys.stderr )
results_list = self.Parser.scrape( "results_list", fetch_results.content )
return results_list
def get_magnet(self, url):
url = "https://" + self.config.proxy + url
try:
fetch_results = self.client.get(url)
except requests.exceptions.RequestException as e:
print( e, file=sys.stderr )
magnet = self.Parser.scrape( "magnet_link", fetch_results.content )
return magnet
@ -71,26 +78,40 @@ class Scraper:
results_buffer = list()
for tr in resultsTable_xpath:
title = tr.xpath('td[2]/div[1]/a[1]/text()')
seeders = tr.xpath('td[3]/text()')[0]
leechers = tr.xpath('td[4]/text()')[0]
author = tr.xpath('td[2]/font/a/text()')
size_unprocessed = tr.xpath('td[2]/font/text()')[0]
url = tr.xpath('td/div[@class="detName"]/a[@class="detLink"]/@href')[0]
title = Scraper.Parser.scrape_helper( tr, 'td[2]/div[1]/a[1]/text()' )
seeders = Scraper.Parser.scrape_helper( tr, 'td[3]/text()' )
leechers = Scraper.Parser.scrape_helper( tr, 'td[4]/text()' )
url = Scraper.Parser.scrape_helper( tr, 'td/div[@class="detName"]/a[@class="detLink"]/@href' )
size_unprocessed = Scraper.Parser.scrape_helper( tr, 'td[2]/font/text()' )
m = re.search('Size (.+?),', size_unprocessed)
if m:
size = m.group(1)
author = Scraper.Parser.scrape_helper( tr, 'td[2]/font[@class="detDesc"]/*/text()' )
print("Result: {0}".format( Result(title, seeders, leechers, size, author, url) ) )
results_buffer.append(
Result(title, seeders, leechers, size, author, url)
)
# hack
nav = results_buffer.pop()
return results_buffer
@staticmethod
def scrape_helper( tr, xpathq ):
try:
val = tr.xpath( xpathq )[0]
except IndexError:
val = "0"
return val
@staticmethod
def magnet_link( text ):