├── webcollector ├── plugin │ ├── __init__.py │ ├── net.py │ ├── ram.py │ └── redis.py ├── config.py ├── net.py ├── __init__.py ├── filter.py ├── db_manager.py ├── generate.py ├── utils.py ├── fetch.py ├── crawler.py └── model.py ├── .gitignore ├── examples ├── demo_server.py ├── demo_speed.py ├── demo_manual_news_crawler.py ├── demo_auto_news_crawler.py ├── demo_redis_crawler.py ├── demo_detected_filter.py └── demo_custom_http_request.py ├── setup.py ├── test.py ├── README.md └── LICENSE /webcollector/plugin/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | /.idea/ 2 | **/__pycache__/ 3 | /webcollector.egg-info/ 4 | /dist/ 5 | **/*.p -------------------------------------------------------------------------------- /webcollector/config.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | DEFAULT_USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36" 3 | -------------------------------------------------------------------------------- /examples/demo_server.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from flask import Flask 3 | import time 4 | import random 5 | app = Flask(__name__) 6 | 7 | @app.route("/") 8 | def index(): 9 | time.sleep(2) 10 | return "ok" 11 | 12 | app.run() 13 | -------------------------------------------------------------------------------- /webcollector/net.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | 3 | 4 | class Requester(object): 5 | 6 | def __enter__(self): 7 | return self 8 | 9 | def __exit__(self, exc_type, exc_val, exc_tb): 10 | pass 11 | 12 | def get_response(self, crawl_datum): 13 | raise NotImplementedError() -------------------------------------------------------------------------------- /webcollector/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | import logging 3 | import sys 4 | 5 | from webcollector.plugin.redis import RedisCrawler 6 | from webcollector.plugin.ram import RamCrawler 7 | 8 | 9 | logging.basicConfig( 10 | stream=sys.stdout, 11 | level=logging.INFO, 12 | format='%(asctime)s %(levelname)s: %(message)s') 13 | -------------------------------------------------------------------------------- /webcollector/filter.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | class Filter(object): 3 | def filter(self, crawl_datum): 4 | return None 5 | 6 | 7 | class HistoryFilter(Filter): 8 | def __init__(self, history): 9 | self.history = history 10 | 11 | def filter(self, crawl_datum): 12 | if crawl_datum.key in self.history: 13 | return crawl_datum 14 | else: 15 | return None 16 | -------------------------------------------------------------------------------- /webcollector/db_manager.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | 3 | 4 | class DBManager(object): 5 | 6 | def inject(self, seeds, forced=False): 7 | pass 8 | 9 | def init_fetch_and_detect(self): 10 | pass 11 | 12 | def write_fetch(self, crawl_datum): 13 | pass 14 | 15 | def write_detect(self, crawl_datum): 16 | pass 17 | 18 | def merge(self): 19 | pass 20 | 21 | def create_generator(self): 22 | return None 23 | 24 | def clear(self): 25 | pass 26 | 27 | def open(self): 28 | pass 29 | 30 | def close(self): 31 | pass 32 | -------------------------------------------------------------------------------- /examples/demo_speed.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | import webcollector as wc 3 | import time 4 | 5 | 6 | class RubyChinaCrawler(wc.RamCrawler): 7 | def __init__(self): 8 | super().__init__(auto_detect=False) 9 | self.num_threads = 10 10 | self.add_seeds(["https://ruby-china.org/topics?page={}".format(i) for i in range(1, 40)]) 11 | 12 | def visit(self, page, detected): 13 | print("start_visit", page.url) 14 | # time.sleep(4) 15 | print("end_visit", page.url) 16 | 17 | 18 | crawler = RubyChinaCrawler() 19 | start = time.time() 20 | crawler.start(10) 21 | print(time.time() - start) 22 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup, find_packages 2 | 3 | setup( 4 | name="webcollector", 5 | version="0.0.5-alpha", 6 | author="Jun Hu", 7 | packages=find_packages( 8 | exclude=[ 9 | 'examples' 10 | ] 11 | ), 12 | install_requires=[ 13 | "html5lib", 14 | "aiohttp", 15 | "BeautifulSoup4", 16 | "redis", 17 | "requests" 18 | ], 19 | description="WebCollector-Python is an open source web crawler framework based on Python.It provides some simple interfaces for crawling the Web,you can setup a multi-threaded web crawler in less than 5 minutes.", 20 | license="GNU General Public License v3.0 (See LICENSE)", 21 | url="https://github.com/CrawlScript/WebCollector-Python" 22 | ) -------------------------------------------------------------------------------- /examples/demo_manual_news_crawler.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | import webcollector as wc 3 | 4 | 5 | class NewsCrawler(wc.RamCrawler): 6 | def __init__(self): 7 | super().__init__(auto_detect=False) 8 | self.num_threads = 10 9 | self.add_seed("https://github.blog/") 10 | 11 | def visit(self, page, detected): 12 | 13 | detected.extend(page.links("https://github.blog/[0-9]+.*")) 14 | 15 | if page.match_url("https://github.blog/[0-9]+.*"): 16 | title = page.select("h1.lh-condensed")[0].text.strip() 17 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 18 | print("\nURL: ", page.url) 19 | print("TITLE: ", title) 20 | print("CONTENT: ", content[:50], "...") 21 | 22 | 23 | crawler = NewsCrawler() 24 | crawler.start(10) 25 | -------------------------------------------------------------------------------- /examples/demo_auto_news_crawler.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | import webcollector as wc 3 | 4 | 5 | class NewsCrawler(wc.RamCrawler): 6 | def __init__(self): 7 | super().__init__(auto_detect=True) 8 | self.num_threads = 10 9 | self.add_seed("https://github.blog/") 10 | self.add_regex("+https://github.blog/[0-9]+.*") 11 | self.add_regex("-.*#.*") # do not detect urls that contain "#" 12 | 13 | def visit(self, page, detected): 14 | if page.match_url("https://github.blog/[0-9]+.*"): 15 | title = page.select("h1.lh-condensed")[0].text.strip() 16 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 17 | print("\nURL: ", page.url) 18 | print("TITLE: ", title) 19 | print("CONTENT: ", content[:50], "...") 20 | 21 | 22 | crawler = NewsCrawler() 23 | crawler.start(10) 24 | -------------------------------------------------------------------------------- /examples/demo_redis_crawler.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from redis import StrictRedis 3 | import webcollector as wc 4 | 5 | 6 | class NewsCrawler(wc.RedisCrawler): 7 | 8 | def __init__(self): 9 | super().__init__(redis_client=StrictRedis("127.0.0.1"), 10 | db_prefix="news", 11 | auto_detect=True) 12 | self.num_threads = 10 13 | self.resumable = True # you can resume crawling after shutdown 14 | self.add_seed("https://github.blog/") 15 | self.add_regex("+https://github.blog/[0-9]+.*") 16 | self.add_regex("-.*#.*") # do not detect urls that contain "#" 17 | 18 | def visit(self, page, detected): 19 | if page.match_url("https://github.blog/[0-9]+.*"): 20 | title = page.select("h1.lh-condensed")[0].text.strip() 21 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 22 | print("\nURL: ", page.url) 23 | print("TITLE: ", title) 24 | print("CONTENT: ", content[:50], "...") 25 | 26 | 27 | crawler = NewsCrawler() 28 | crawler.start(10) 29 | -------------------------------------------------------------------------------- /webcollector/generate.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from webcollector.model import CrawlDatum 3 | from webcollector.filter import Filter 4 | 5 | 6 | class Generator(object): 7 | 8 | def __init__(self): 9 | self.num_generated = 0 10 | self.generator_filter = None 11 | 12 | def next(self): 13 | while True: 14 | crawl_datum = self._next() 15 | if crawl_datum is None: 16 | return crawl_datum 17 | else: 18 | if self.generator_filter is None: 19 | return crawl_datum 20 | else: 21 | crawl_datum = self.generator_filter.filter(crawl_datum) 22 | if crawl_datum is None: 23 | continue 24 | else: 25 | self.num_generated += 1 26 | return crawl_datum 27 | 28 | def _next(self): 29 | return None 30 | 31 | 32 | class StatusGeneratorFilter(Filter): 33 | def filter(self, crawl_datum): 34 | if crawl_datum.status != CrawlDatum.STATUS_DB_SUCCESS: 35 | return crawl_datum 36 | else: 37 | return None -------------------------------------------------------------------------------- /examples/demo_detected_filter.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | import webcollector as wc 3 | from webcollector.filter import Filter 4 | import re 5 | 6 | 7 | class RegexDetectedFilter(Filter): 8 | def filter(self, crawl_datum): 9 | if re.fullmatch("https://github.blog/2019-02.*", crawl_datum.url): 10 | return crawl_datum 11 | else: 12 | print("filtered by detected_filter: {}".format(crawl_datum.brief_info())) 13 | return None 14 | 15 | 16 | class NewsCrawler(wc.RamCrawler): 17 | def __init__(self): 18 | super().__init__(auto_detect=True, detected_filter=RegexDetectedFilter()) 19 | self.num_threads = 10 20 | self.add_seed("https://github.blog/") 21 | 22 | def visit(self, page, detected): 23 | 24 | detected.extend(page.links("https://github.blog/[0-9]+.*")) 25 | 26 | if page.match_url("https://github.blog/[0-9]+.*"): 27 | title = page.select("h1.lh-condensed")[0].text.strip() 28 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 29 | print("\nURL: ", page.url) 30 | print("TITLE: ", title) 31 | print("CONTENT: ", content[:50], "...") 32 | 33 | 34 | crawler = NewsCrawler() 35 | crawler.start(10) 36 | -------------------------------------------------------------------------------- /webcollector/utils.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | 3 | import re 4 | 5 | 6 | def url_matches(url, url_regex): 7 | if isinstance(url_regex, str): 8 | return re.fullmatch(url_regex, url) is not None 9 | else: 10 | return url_regex.fullmatch(url) is not None 11 | 12 | 13 | class RegexRule(object): 14 | def __init__(self): 15 | self.pos_regexes = [] 16 | self.neg_regexes = [] 17 | 18 | def add(self, regex): 19 | start_char = regex[0] 20 | if start_char == '+': 21 | self.add_pos(regex[1:]) 22 | elif start_char == '-': 23 | self.add_neg(regex[1:]) 24 | else: 25 | self.add_pos(regex) 26 | 27 | def add_pos(self, pos_regex): 28 | self.pos_regexes.append(re.compile(pos_regex)) 29 | 30 | def add_neg(self, neg_regex): 31 | self.neg_regexes.append(re.compile(neg_regex)) 32 | 33 | # match rule: 34 | # - must match at least one pos rule 35 | # - must not match any neg rule 36 | def matches(self, url): 37 | for neg_rule in self.neg_regexes: 38 | if neg_rule.fullmatch(url) is not None: 39 | return False 40 | for pos_rule in self.pos_regexes: 41 | if pos_rule.fullmatch(url) is not None: 42 | return True 43 | return False 44 | 45 | -------------------------------------------------------------------------------- /webcollector/plugin/net.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from webcollector.config import DEFAULT_USER_AGENT 3 | from webcollector.model import Page 4 | from webcollector.net import Requester 5 | import requests 6 | 7 | 8 | class HttpRequester(Requester): 9 | 10 | def get_response(self, crawl_datum): 11 | headers = {"User-Agent": DEFAULT_USER_AGENT} 12 | response = requests.get(crawl_datum.url, headers=headers) 13 | 14 | code = response.status_code 15 | content = response.content 16 | encoding = response.encoding 17 | content_type = response.headers["Content-Type"] 18 | 19 | crawl_datum.code = code 20 | page = Page(crawl_datum, content, content_type=content_type, http_charset=encoding) 21 | 22 | return page 23 | 24 | 25 | # class AioHttpRequester(Requester): 26 | # 27 | # def __init__(self): 28 | # self.session = None 29 | # 30 | # def create_async_context_manager(self): 31 | # self.session = aiohttp.ClientSession() 32 | # return self.session 33 | # 34 | # def request(self, crawl_datum): 35 | # return self.session.get( 36 | # crawl_datum.url, 37 | # headers={"User-Agent": DEFAULT_USER_AGENT} 38 | # ) 39 | # 40 | # async def get_response(self, crawl_datum): 41 | # # async with self.session.get(crawl_datum.url) as response: 42 | # async with self.request(crawl_datum) as response: 43 | # code = response.status 44 | # content = await response.content.read() 45 | # encoding = response.get_encoding() 46 | # content_type = response.content_type 47 | # crawl_datum.code = code 48 | # page = Page(crawl_datum, content, content_type=content_type, http_charset=encoding) 49 | # return page 50 | 51 | 52 | 53 | -------------------------------------------------------------------------------- /examples/demo_custom_http_request.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | 3 | import webcollector as wc 4 | from webcollector.model import Page 5 | from webcollector.plugin.net import HttpRequester 6 | 7 | import requests 8 | 9 | 10 | class MyRequester(HttpRequester): 11 | def get_response(self, crawl_datum): 12 | # custom http request 13 | headers = { 14 | "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36" 15 | } 16 | 17 | print("sending request with MyRequester") 18 | 19 | # send request and get response 20 | response = requests.get(crawl_datum.url, headers=headers) 21 | 22 | # update code 23 | crawl_datum.code = response.status_code 24 | 25 | # wrap http response as a Page object 26 | page = Page(crawl_datum, 27 | response.content, 28 | content_type=response.headers["Content-Type"], 29 | http_charset=response.encoding) 30 | 31 | return page 32 | 33 | 34 | class NewsCrawler(wc.RamCrawler): 35 | def __init__(self): 36 | super().__init__(auto_detect=True) 37 | self.num_threads = 10 38 | 39 | # set requester to enable MyRequester 40 | self.requester = MyRequester() 41 | 42 | self.add_seed("https://github.blog/") 43 | self.add_regex("+https://github.blog/[0-9]+.*") 44 | self.add_regex("-.*#.*") # do not detect urls that contain "#" 45 | 46 | def visit(self, page, detected): 47 | if page.match_url("https://github.blog/[0-9]+.*"): 48 | title = page.select("h1.lh-condensed")[0].text.strip() 49 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 50 | print("\nURL: ", page.url) 51 | print("TITLE: ", title) 52 | print("CONTENT: ", content[:50], "...") 53 | 54 | 55 | crawler = NewsCrawler() 56 | crawler.start(10) -------------------------------------------------------------------------------- /test.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | 3 | import asyncio 4 | import requests 5 | import random 6 | import threading 7 | 8 | 9 | 10 | import asyncio 11 | import requests 12 | from concurrent.futures import ThreadPoolExecutor 13 | import time 14 | 15 | url = "http://127.0.0.1:5000" 16 | 17 | loop = asyncio.get_event_loop() 18 | 19 | 20 | async def cor(): 21 | print("c-start") 22 | await asyncio.sleep(4) 23 | print("c-end") 24 | 25 | 26 | async def main(): 27 | tasks = [loop.create_task(cor()) for _ in range(10)] 28 | print("finish tasks======") 29 | for i, task in enumerate(tasks): 30 | print("start", i) 31 | time.sleep(5) 32 | await task 33 | print("end", i) 34 | 35 | loop.run_until_complete(main()) 36 | 37 | adfads 38 | 39 | pool = ThreadPoolExecutor(20) 40 | 41 | 42 | 43 | def request(i): 44 | print("start", i) 45 | time.sleep(5) 46 | text = requests.get(url).text 47 | print("content:", i, text) 48 | print(threading.get_ident()) 49 | return text 50 | 51 | 52 | # f0 = loop.run_in_executor(pool, request) 53 | # f1 = loop.run_in_executor(pool, request) 54 | # futures = [loop.run_in_executor(pool, request, i) for i in range(20)] 55 | # futures = [loop.run_in_executor(None, requests.get, "http://127.0.0.1:5000") for _ in range(10)] 56 | # print("======") 57 | 58 | 59 | async def cor(i): 60 | for j in range(20): 61 | future = loop.run_in_executor(pool, request, "{}_{}".format(i, j)) 62 | await future 63 | print("cor", i) 64 | print("end-cor", i) 65 | 66 | loop.run_until_complete(asyncio.gather(*[cor(i) for i in range(10)])) 67 | 68 | 69 | # async def main(): 70 | # # for future in futures: 71 | # for i in range(10): 72 | # # future = loop.run_in_executor(pool, request) 73 | # await futures[i] 74 | # print("end", i) 75 | # 76 | # loop.run_until_complete(main()) 77 | 78 | # async def test(): 79 | # print("start") 80 | # # await asyncio.sleep(2) 81 | # request_future = loop.run_in_executor(pool, request) 82 | # result = await request_future 83 | # print("end") 84 | # 85 | # 86 | # 87 | # 88 | # async def main(): 89 | # tasks = [loop.create_task(test()) for _ in range(10)] 90 | # for i in range(10): 91 | # await tasks[i] 92 | # print("task end", i) 93 | # 94 | # 95 | # loop.run_until_complete(main()) -------------------------------------------------------------------------------- /webcollector/plugin/ram.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from webcollector.crawler import AutoDetectCrawler 3 | from webcollector.db_manager import DBManager 4 | from webcollector.generate import Generator 5 | from webcollector.model import CrawlDatum 6 | 7 | 8 | class RamDB(object): 9 | def __init__(self): 10 | self.crawl_db = {} 11 | self.fetch_db = None 12 | self.detect_db = None 13 | 14 | 15 | class RamDBGenerator(Generator): 16 | 17 | def __init__(self, ram_db): 18 | super().__init__() 19 | self.ram_db = ram_db 20 | self.iter = iter(self.ram_db.crawl_db.values()) 21 | 22 | def _next(self) -> CrawlDatum: 23 | try: 24 | return next(self.iter) 25 | except StopIteration: 26 | return None 27 | 28 | 29 | class RamDBManager(DBManager): 30 | def __init__(self, ram_db): 31 | self.ram_db = ram_db 32 | 33 | def inject(self, seeds, forced=False): 34 | for seed in seeds: 35 | if isinstance(seed, str): 36 | seed = CrawlDatum(seed) 37 | if not forced and seed.key in self.ram_db.crawl_db: 38 | continue 39 | self.ram_db.crawl_db[seed.key] = seed 40 | 41 | def create_generator(self): 42 | return RamDBGenerator(self.ram_db) 43 | 44 | def init_fetch_and_detect(self): 45 | self.ram_db.fetch_db = {} 46 | self.ram_db.detect_db = {} 47 | 48 | def write_fetch(self, crawl_datum): 49 | self.ram_db.fetch_db[crawl_datum.key] = crawl_datum 50 | 51 | def write_detect(self, crawl_datum): 52 | self.ram_db.detect_db[crawl_datum.key] = crawl_datum 53 | 54 | def merge(self): 55 | print("merging......") 56 | if self.ram_db.fetch_db is not None: 57 | for crawl_datum in self.ram_db.fetch_db.values(): 58 | self.ram_db.crawl_db[crawl_datum.key] = crawl_datum 59 | self.ram_db.fetch_db = None 60 | 61 | if self.ram_db.detect_db is not None: 62 | for crawl_datum in self.ram_db.detect_db.values(): 63 | if crawl_datum.key not in self.ram_db.crawl_db: 64 | self.ram_db.crawl_db[crawl_datum.key] = crawl_datum 65 | self.ram_db.detect_db = None 66 | 67 | 68 | class RamCrawler(AutoDetectCrawler): 69 | def __init__(self, auto_detect, **kwargs): 70 | self.ram_db = RamDB() 71 | super().__init__(RamDBManager(self.ram_db), auto_detect, **kwargs) 72 | 73 | -------------------------------------------------------------------------------- /webcollector/plugin/redis.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from redis import StrictRedis 3 | 4 | from webcollector.crawler import AutoDetectCrawler 5 | from webcollector.db_manager import DBManager 6 | from webcollector.generate import Generator 7 | from webcollector.model import CrawlDatum 8 | 9 | 10 | class RedisDBGenerator(Generator): 11 | 12 | def __init__(self, redis_db_manager): 13 | super().__init__() 14 | self.history_keys = set() 15 | self.iter = redis_db_manager.redis_client.hscan_iter( 16 | redis_db_manager.crawl_db 17 | ) 18 | 19 | def _next(self) -> CrawlDatum: 20 | try: 21 | while True: 22 | key, crawl_datum_json = next(self.iter) 23 | if key in self.history_keys: 24 | continue 25 | else: 26 | self.history_keys.add(key) 27 | return CrawlDatum.from_json(crawl_datum_json) 28 | except StopIteration: 29 | return None 30 | 31 | 32 | class RedisDBManager(DBManager): 33 | def __init__(self, redis_client: StrictRedis, db_prefix): 34 | self.redis_client = redis_client 35 | self.db_prefix = db_prefix 36 | self.crawl_db = "{}_crawl".format(db_prefix) 37 | self.fetch_db = "{}_fetch".format(db_prefix) 38 | self.detect_db = "{}_detect".format(db_prefix) 39 | 40 | def open(self): 41 | pass 42 | 43 | def close(self): 44 | pass 45 | 46 | def clear(self): 47 | self.redis_client.delete(self.crawl_db) 48 | self.redis_client.delete(self.fetch_db) 49 | self.redis_client.delete(self.detect_db) 50 | 51 | def inject(self, seeds, forced=False): 52 | for seed in seeds: 53 | if isinstance(seed, str): 54 | seed = CrawlDatum(seed) 55 | if not forced and self.redis_client.hexists(self.crawl_db, seed.key): 56 | continue 57 | self.redis_client.hset(self.crawl_db, seed.key, seed.to_json()) 58 | 59 | def create_generator(self): 60 | return RedisDBGenerator(self) 61 | 62 | def init_fetch_and_detect(self): 63 | pass 64 | 65 | def write_fetch(self, crawl_datum): 66 | self.redis_client.hset(self.fetch_db, crawl_datum.key, crawl_datum.to_json()) 67 | 68 | def write_detect(self, crawl_datum): 69 | self.redis_client.hset(self.detect_db, crawl_datum.key, crawl_datum.to_json()) 70 | 71 | def merge(self): 72 | print("merging......") 73 | if self.redis_client.exists(self.fetch_db): 74 | for _, crawl_datum_json in self.redis_client.hscan_iter(self.fetch_db): 75 | crawl_datum = CrawlDatum.from_json(crawl_datum_json) 76 | self.redis_client.hset(self.crawl_db, crawl_datum.key, crawl_datum.to_json()) 77 | self.redis_client.delete(self.fetch_db) 78 | 79 | if self.redis_client.exists(self.detect_db): 80 | for key, crawl_datum_json in self.redis_client.hscan_iter(self.detect_db): 81 | if not self.redis_client.hexists(self.crawl_db, key): 82 | crawl_datum = CrawlDatum.from_json(crawl_datum_json) 83 | self.redis_client.hset(self.crawl_db, crawl_datum.key, crawl_datum.to_json()) 84 | self.redis_client.delete(self.detect_db) 85 | 86 | 87 | class RedisCrawler(AutoDetectCrawler): 88 | def __init__(self, redis_client, db_prefix, auto_detect, **kwargs): 89 | super().__init__(RedisDBManager(redis_client, db_prefix), auto_detect, **kwargs) 90 | 91 | -------------------------------------------------------------------------------- /webcollector/fetch.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | import queue 3 | import asyncio 4 | import logging 5 | from webcollector.model import Page, CrawlDatums, CrawlDatum 6 | 7 | logger = logging.getLogger(__name__) 8 | 9 | 10 | class Fetcher(object): 11 | def __init__(self, 12 | db_manager, 13 | requester, 14 | execute_func, 15 | generator_filter=None, 16 | detected_filter=None, 17 | num_threads=10): 18 | self.fetch_queue = None 19 | self.feed_stopped = None 20 | self.generator = None 21 | self.generator_filter = generator_filter 22 | self.detected_filter = detected_filter 23 | self.feeder = None 24 | self.buffer_size = 1000 25 | self.db_manager = db_manager 26 | 27 | self.requester = requester 28 | self.execute_func = execute_func 29 | self.num_threads = num_threads 30 | 31 | self.loop = None 32 | 33 | 34 | async def async_start(self): 35 | self.fetch_queue = queue.Queue() 36 | self.feed_stopped = False 37 | self.db_manager.open() 38 | self.db_manager.init_fetch_and_detect() 39 | self.generator = self.db_manager.create_generator() 40 | self.generator.generator_filter = self.generator_filter 41 | 42 | # async with self.requester.create_async_context_manager(): 43 | # coroutines = [self.fetch_coroutine(self.execute_func) for _ in range(self.num_threads)] 44 | # await asyncio.gather(*coroutines) 45 | with self.requester: 46 | coroutines = [self.fetch_coroutine(self.execute_func) for _ in range(self.num_threads)] 47 | await asyncio.gather(*coroutines) 48 | self.db_manager.close() 49 | 50 | def start(self): 51 | self.loop = asyncio.get_event_loop() 52 | self.loop.run_until_complete(self.async_start()) 53 | return self.generator.num_generated 54 | 55 | def feed(self): 56 | for i in range(self.buffer_size): 57 | crawl_datum = self.generator.next() 58 | if crawl_datum is None: 59 | self.feed_stopped = True 60 | return 61 | else: 62 | self.fetch_queue.put(crawl_datum) 63 | 64 | async def fetch_coroutine(self, execute_func): 65 | while True: 66 | if self.fetch_queue.empty(): 67 | if self.feed_stopped: 68 | break 69 | self.feed() 70 | else: 71 | crawl_datum = self.fetch_queue.get(block=False) 72 | try: 73 | # loop = asyncio.get_event_loop() 74 | request_future = self.loop.run_in_executor(None, self.requester.get_response, crawl_datum) 75 | page = await request_future 76 | # page = await self.requester.get_response(crawl_datum) 77 | detected = CrawlDatums() 78 | execute_func(page, detected) 79 | 80 | crawl_datum.status = CrawlDatum.STATUS_DB_SUCCESS 81 | 82 | if self.detected_filter is not None: 83 | filtered_detected = CrawlDatums() 84 | for detected_crawl_datum in detected: 85 | detected_crawl_datum = self.detected_filter.filter(detected_crawl_datum) 86 | if detected_crawl_datum is not None: 87 | filtered_detected.append(detected_crawl_datum) 88 | else: 89 | filtered_detected = detected 90 | 91 | for detected_crawl_datum in filtered_detected: 92 | self.db_manager.write_detect(detected_crawl_datum) 93 | logger.info("done: {}".format(crawl_datum.brief_info())) 94 | except Exception as e: 95 | logger.error("failed: {}".format(crawl_datum.brief_info()), exc_info=True) 96 | crawl_datum.status = CrawlDatum.STATUS_DB_FAILED 97 | 98 | crawl_datum.num_fetched += 1 99 | self.db_manager.write_fetch(crawl_datum) 100 | -------------------------------------------------------------------------------- /webcollector/crawler.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from urllib.parse import urljoin 3 | 4 | from webcollector.fetch import Fetcher 5 | from webcollector.generate import StatusGeneratorFilter 6 | from webcollector.model import Page, CrawlDatums 7 | from webcollector.plugin.net import HttpRequester 8 | from webcollector.utils import RegexRule 9 | 10 | import logging 11 | import time 12 | 13 | logger = logging.getLogger(__name__) 14 | 15 | 16 | class Crawler(object): 17 | def __init__(self, 18 | db_manager, 19 | requester=HttpRequester(), 20 | generator_filter=StatusGeneratorFilter(), 21 | detected_filter=None): 22 | self.db_manager = db_manager 23 | self.requester = requester 24 | self.generator_filter = generator_filter 25 | self.detected_filter = detected_filter 26 | self.fetcher = None 27 | self.num_threads = 10 28 | self.resumable = None 29 | 30 | self.seeds = CrawlDatums() 31 | self.forced_seeds = CrawlDatums() 32 | 33 | def add_seed(self, url_or_datum, type=None, forced=False): 34 | if forced: 35 | return self.forced_seeds.append(url_or_datum).set_type(type) 36 | else: 37 | return self.seeds.append(url_or_datum).set_type(type) 38 | 39 | def add_seeds(self, urls_or_datums, type=None, forced=False): 40 | crawl_datums = [] 41 | for url_or_datum in urls_or_datums: 42 | crawl_datum = self.add_seed(url_or_datum, type=type, forced=forced) 43 | crawl_datums.append(crawl_datum) 44 | return crawl_datums 45 | 46 | def inject(self): 47 | self.db_manager.inject(self.seeds, forced=False) 48 | self.db_manager.inject(self.forced_seeds, forced=True) 49 | 50 | # def add_seed_and_return(self, url_or_datum): 51 | # crawl_datum = CrawlDatum.convert_from_item(url_or_datum) 52 | # self.seeds.append(crawl_datum) 53 | # return crawl_datum 54 | 55 | # def add_seeds_and_return(self, urls_or_datums): 56 | # crawl_datums = CrawlDatum.convert_from_list(urls_or_datums) 57 | # self.seeds.extend(crawl_datums) 58 | # return crawl_datums 59 | 60 | def execute(self, page, detected): 61 | pass 62 | 63 | def start_once(self, depth_index): 64 | self.db_manager.merge() 65 | self.fetcher = Fetcher( 66 | self.db_manager, 67 | self.requester, 68 | execute_func=self.execute, 69 | generator_filter=self.generator_filter, 70 | detected_filter=self.detected_filter, 71 | num_threads=self.num_threads 72 | ) 73 | return self.fetcher.start() 74 | 75 | def start(self, depth): 76 | if not self.resumable: 77 | self.db_manager.clear() 78 | if len(self.seeds) == 0 and len(self.forced_seeds) == 0: 79 | raise Exception("Please add at least one seed") 80 | self.inject() 81 | for depth_index in range(depth): 82 | print("start depth {}".format(depth_index)) 83 | start_time = time.time() 84 | num_generated = self.start_once(depth_index) 85 | cost_time = time.time() - start_time 86 | logger.info("depth {} finish: \n\ttotal urls:\t{}\n\ttotal time:\t{} seconds" 87 | .format(depth_index, num_generated, cost_time)) 88 | if num_generated == 0: 89 | break 90 | 91 | 92 | class AutoDetectCrawler(Crawler): 93 | 94 | def __init__(self, db_manager, auto_detect, **kwargs): 95 | super().__init__(db_manager, **kwargs) 96 | self.auto_detect = auto_detect 97 | self.regex_rule = RegexRule() 98 | 99 | def add_regex(self, regex): 100 | self.regex_rule.add(regex) 101 | 102 | def execute(self, page, detected): 103 | self.visit(page, detected) 104 | if self.auto_detect: 105 | self.detect_links(page, detected) 106 | 107 | def visit(self, page, detected): 108 | pass 109 | 110 | def detect_links(self, page: Page, detected): 111 | if page.content_type is not None and "text/html" in page.content_type: 112 | link_eles = page.select("a[href]") 113 | for link_ele in link_eles: 114 | href = link_ele["href"] 115 | abs_href = urljoin(page.url, href) 116 | if self.regex_rule.matches(abs_href): 117 | detected.append(abs_href) 118 | -------------------------------------------------------------------------------- /webcollector/model.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from urllib.parse import urljoin 3 | import chardet 4 | from bs4 import BeautifulSoup 5 | import json 6 | 7 | 8 | # A CrawlDatum corresponds to a task description (usually for a webpage) 9 | from webcollector.utils import url_matches 10 | 11 | 12 | class CrawlDatum(object): 13 | STATUS_DB_UNEXECUTED = 0 14 | STATUS_DB_FAILED = 1 15 | STATUS_DB_SUCCESS = 5 16 | CODE_NOT_SET = -1 17 | 18 | META_KEY_SYS_TYPE = "sys_type" 19 | 20 | def __init__(self, url, 21 | key=None, 22 | type=None, 23 | meta_dict=None, 24 | code=CODE_NOT_SET, 25 | status=STATUS_DB_UNEXECUTED, 26 | num_fetched=0): 27 | self.url = url 28 | self.key = key if key is not None else url 29 | self.type = type 30 | self.meta_dict = meta_dict 31 | self.code = code 32 | self.status = status 33 | self.num_fetched = num_fetched 34 | 35 | def set_key(self, key): 36 | self.key = key 37 | return self 38 | 39 | def set_type(self, type): 40 | self.type = type 41 | return self 42 | 43 | def set_url(self, url): 44 | self.url = url 45 | return self 46 | 47 | def set_meta_dict(self, meta_dict): 48 | self.meta_dict = meta_dict 49 | return self.meta_dict 50 | 51 | def set_meta_item(self, meta_key, meta_value): 52 | if self.meta_dict is None: 53 | self.meta_dict = {} 54 | self.meta_dict[meta_key] = meta_value 55 | return self 56 | 57 | def match_type(self, type): 58 | return self.type == type 59 | 60 | def match_url(self, url_regex): 61 | return url_matches(self.url, url_regex) 62 | 63 | @classmethod 64 | def convert_from_item(cls, url_or_datum): 65 | if isinstance(url_or_datum, CrawlDatum): 66 | return url_or_datum 67 | else: 68 | return CrawlDatum(url_or_datum) 69 | 70 | def brief_info(self): 71 | infos = [] 72 | if self.code != CrawlDatum.CODE_NOT_SET: 73 | infos.append("[{}]".format(self.code)) 74 | infos.append("Key: {} (URL: {})".format(self.key, self.url)) 75 | return " ".join(infos) 76 | 77 | def to_dict(self): 78 | dict_data = { 79 | "url": self.url, 80 | "key": self.key, 81 | "type": self.type, 82 | "meta_dict": self.meta_dict, 83 | "code": self.code, 84 | "status": self.status, 85 | "num_fetched": self.num_fetched 86 | } 87 | return dict_data 88 | 89 | @classmethod 90 | def from_dict(cls, dict_data): 91 | return CrawlDatum( 92 | url=dict_data["url"], 93 | key=dict_data["key"], 94 | type=dict_data["type"], 95 | meta_dict=dict_data["meta_dict"], 96 | code=dict_data["code"], 97 | status=dict_data["status"], 98 | num_fetched=dict_data["num_fetched"] 99 | ) 100 | 101 | def to_json(self): 102 | return json.dumps(self.to_dict()) 103 | 104 | @classmethod 105 | def from_json(cls, json_str): 106 | return CrawlDatum.from_dict(json.loads(json_str)) 107 | 108 | 109 | class CrawlDatums(list): 110 | 111 | def append(self, url_or_datum): 112 | if isinstance(url_or_datum, CrawlDatum): 113 | crawl_datum = url_or_datum 114 | else: 115 | crawl_datum = CrawlDatum(url_or_datum) 116 | super().append(crawl_datum) 117 | return crawl_datum 118 | 119 | def extend(self, url_or_datums): 120 | crawl_datums = [] 121 | for url_or_datum in url_or_datums: 122 | crawl_datums.append(self.append(url_or_datum)) 123 | return crawl_datums 124 | 125 | def set_type(self, type): 126 | for crawl_datum in self: 127 | crawl_datum.type = type 128 | 129 | def set_meta_item(self, meta_key, meta_value): 130 | for crawl_datum in self: 131 | crawl_datum.set_meta_item(meta_key, meta_value) 132 | 133 | @classmethod 134 | def convert_from_list(cls, urls_or_datums): 135 | return [CrawlDatum.convert_from_item(item) for item in urls_or_datums] 136 | 137 | 138 | # A Page corresponds to the response of a http request 139 | class Page(object): 140 | def __init__(self, crawl_datum, content, content_type=None, http_charset=None): 141 | self.crawl_datum = crawl_datum 142 | # self.code = code 143 | self.content = content 144 | self.content_type = content_type 145 | self.http_charset = http_charset 146 | self._html = None 147 | self._detected_charset = None 148 | self._doc = None 149 | 150 | def abs_url(self, abs_or_relative_url): 151 | return urljoin(self.url, abs_or_relative_url) 152 | 153 | @property 154 | def code(self): 155 | return self.crawl_datum.code 156 | 157 | @property 158 | def url(self): 159 | return self.crawl_datum.url 160 | 161 | @property 162 | def doc(self): 163 | if self._doc is not None: 164 | return self._doc 165 | html = self.html 166 | if html is None: 167 | return None 168 | self._doc = BeautifulSoup(html, features="html5lib") 169 | return self._doc 170 | 171 | def select(self, css_selector): 172 | soup = self.doc 173 | return soup.select(css_selector) 174 | 175 | @property 176 | def html(self): 177 | # cache 178 | if self._html is not None: 179 | return self._html 180 | self._html = self.decode_content() 181 | return self._html 182 | 183 | @property 184 | def type(self): 185 | return self.crawl_datum.type 186 | 187 | def links(self, url_regex=None): 188 | a_eles = self.doc.select("a[href]") 189 | urls = [self.abs_url(a_ele["href"]) for a_ele in a_eles] 190 | if url_regex is None: 191 | return urls 192 | else: 193 | urls = [url for url in urls if url_matches(url, url_regex)] 194 | return urls 195 | 196 | def decode_content(self, charset=None): 197 | # None Content 198 | if self.content is None: 199 | return None 200 | # Manual 201 | if charset is not None: 202 | return self.content.decode(charset) 203 | 204 | # Http Charset 205 | if self.http_charset is not None: 206 | return self.content.decode(self.http_charset) 207 | 208 | # detect 209 | if self._detected_charset is None: 210 | self._detected_charset = chardet.detect(self.content)['encoding'] 211 | if self._detected_charset is None: 212 | return self.content.decode("utf-8") 213 | 214 | return self.content.decode(self._detected_charset) 215 | 216 | def match_type(self, type): 217 | return self.crawl_datum.match_type(type) 218 | 219 | def match_url(self, url_regex): 220 | return self.crawl_datum.match_url(url_regex) 221 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # WebCollector-Python 2 | 3 | WebCollector-Python is an open source web crawler framework based on Python.It provides some simple interfaces for crawling the Web,you can setup a multi-threaded web crawler in less than 5 minutes. 4 | 5 | 6 | ## HomePage 7 | 8 | [https://github.com/CrawlScript/WebCollector-Python](https://github.com/CrawlScript/WebCollector-Python) 9 | 10 | ## WebCollector Java Version 11 | 12 | For better efficiency, WebCollector Java Version is recommended: [https://github.com/CrawlScript/WebCollector](https://github.com/CrawlScript/WebCollector) 13 | 14 | 15 | ## Installation 16 | 17 | ### pip 18 | 19 | ```bash 20 | pip install https://github.com/CrawlScript/WebCollector-Python/archive/master.zip 21 | ``` 22 | 23 | ## Example Index 24 | 25 | 26 | ### Basic 27 | 28 | + [demo_auto_news_crawler.py](examples/demo_auto_news_crawler.py) 29 | + [demo_manual_news_crawler.py](examples/demo_manual_news_crawler.py) 30 | 31 | ## Quickstart 32 | 33 | ### Automatically Detecting URLs 34 | 35 | [demo_auto_news_crawler.py](examples/demo_auto_news_crawler.py): 36 | 37 | ```python 38 | # coding=utf-8 39 | import webcollector as wc 40 | 41 | 42 | class NewsCrawler(wc.RamCrawler): 43 | def __init__(self): 44 | super().__init__(auto_detect=True) 45 | self.num_threads = 10 46 | self.add_seed("https://github.blog/") 47 | self.add_regex("+https://github.blog/[0-9]+.*") 48 | self.add_regex("-.*#.*") # do not detect urls that contain "#" 49 | 50 | def visit(self, page, detected): 51 | if page.match_url("https://github.blog/[0-9]+.*"): 52 | title = page.select("h1.lh-condensed")[0].text.strip() 53 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 54 | print("\nURL: ", page.url) 55 | print("TITLE: ", title) 56 | print("CONTENT: ", content[:50], "...") 57 | 58 | 59 | crawler = NewsCrawler() 60 | crawler.start(10) 61 | ``` 62 | 63 | ### Manually Detecting URLs 64 | 65 | [demo_manual_news_crawler.py](examples/demo_manual_news_crawler.py): 66 | 67 | ```python 68 | # coding=utf-8 69 | import webcollector as wc 70 | 71 | 72 | class NewsCrawler(wc.RamCrawler): 73 | def __init__(self): 74 | super().__init__(auto_detect=False) 75 | self.num_threads = 10 76 | self.add_seed("https://github.blog/") 77 | 78 | def visit(self, page, detected): 79 | 80 | detected.extend(page.links("https://github.blog/[0-9]+.*")) 81 | 82 | if page.match_url("https://github.blog/[0-9]+.*"): 83 | title = page.select("h1.lh-condensed")[0].text.strip() 84 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 85 | print("\nURL: ", page.url) 86 | print("TITLE: ", title) 87 | print("CONTENT: ", content[:50], "...") 88 | 89 | 90 | crawler = NewsCrawler() 91 | crawler.start(10) 92 | ``` 93 | 94 | ### Filter Detected URLs by detected_filter Plugin 95 | 96 | [demo_detected_filter.py](examples/demo_detected_filter.py): 97 | 98 | ```python 99 | # coding=utf-8 100 | import webcollector as wc 101 | from webcollector.filter import Filter 102 | import re 103 | 104 | 105 | class RegexDetectedFilter(Filter): 106 | def filter(self, crawl_datum): 107 | if re.fullmatch("https://github.blog/2019-02.*", crawl_datum.url): 108 | return crawl_datum 109 | else: 110 | print("filtered by detected_filter: {}".format(crawl_datum.brief_info())) 111 | return None 112 | 113 | 114 | class NewsCrawler(wc.RamCrawler): 115 | def __init__(self): 116 | super().__init__(auto_detect=True, detected_filter=RegexDetectedFilter()) 117 | self.num_threads = 10 118 | self.add_seed("https://github.blog/") 119 | 120 | def visit(self, page, detected): 121 | 122 | detected.extend(page.links("https://github.blog/[0-9]+.*")) 123 | 124 | if page.match_url("https://github.blog/[0-9]+.*"): 125 | title = page.select("h1.lh-condensed")[0].text.strip() 126 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 127 | print("\nURL: ", page.url) 128 | print("TITLE: ", title) 129 | print("CONTENT: ", content[:50], "...") 130 | 131 | 132 | crawler = NewsCrawler() 133 | crawler.start(10) 134 | ``` 135 | 136 | 137 | ### Resume Crawling by RedisCrawler 138 | 139 | [demo_redis_crawler.py](examples/demo_redis_crawler.py): 140 | 141 | 142 | ```python 143 | # coding=utf-8 144 | from redis import StrictRedis 145 | import webcollector as wc 146 | 147 | 148 | class NewsCrawler(wc.RedisCrawler): 149 | 150 | def __init__(self): 151 | super().__init__(redis_client=StrictRedis("127.0.0.1"), 152 | db_prefix="news", 153 | auto_detect=True) 154 | self.num_threads = 10 155 | self.resumable = True # you can resume crawling after shutdown 156 | self.add_seed("https://github.blog/") 157 | self.add_regex("+https://github.blog/[0-9]+.*") 158 | self.add_regex("-.*#.*") # do not detect urls that contain "#" 159 | 160 | def visit(self, page, detected): 161 | if page.match_url("https://github.blog/[0-9]+.*"): 162 | title = page.select("h1.lh-condensed")[0].text.strip() 163 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 164 | print("\nURL: ", page.url) 165 | print("TITLE: ", title) 166 | print("CONTENT: ", content[:50], "...") 167 | 168 | 169 | crawler = NewsCrawler() 170 | crawler.start(10) 171 | 172 | ``` 173 | 174 | ### Custom Http Request with Requests 175 | 176 | [demo_custom_http_request.py](examples/demo_custom_http_request.py): 177 | 178 | 179 | ```python 180 | # coding=utf-8 181 | 182 | import webcollector as wc 183 | from webcollector.model import Page 184 | from webcollector.plugin.net import HttpRequester 185 | 186 | import requests 187 | 188 | 189 | class MyRequester(HttpRequester): 190 | def get_response(self, crawl_datum): 191 | # custom http request 192 | headers = { 193 | "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36" 194 | } 195 | 196 | print("sending request with MyRequester") 197 | 198 | # send request and get response 199 | response = requests.get(crawl_datum.url, headers=headers) 200 | 201 | # update code 202 | crawl_datum.code = response.status_code 203 | 204 | # wrap http response as a Page object 205 | page = Page(crawl_datum, 206 | response.content, 207 | content_type=response.headers["Content-Type"], 208 | http_charset=response.encoding) 209 | 210 | return page 211 | 212 | 213 | class NewsCrawler(wc.RamCrawler): 214 | def __init__(self): 215 | super().__init__(auto_detect=True) 216 | self.num_threads = 10 217 | 218 | # set requester to enable MyRequester 219 | self.requester = MyRequester() 220 | 221 | self.add_seed("https://github.blog/") 222 | self.add_regex("+https://github.blog/[0-9]+.*") 223 | self.add_regex("-.*#.*") # do not detect urls that contain "#" 224 | 225 | def visit(self, page, detected): 226 | if page.match_url("https://github.blog/[0-9]+.*"): 227 | title = page.select("h1.lh-condensed")[0].text.strip() 228 | content = page.select("div.markdown-body")[0].text.replace("\n", " ").strip() 229 | print("\nURL: ", page.url) 230 | print("TITLE: ", title) 231 | print("CONTENT: ", content[:50], "...") 232 | 233 | 234 | crawler = NewsCrawler() 235 | crawler.start(10) 236 | ``` -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | --------------------------------------------------------------------------------