def _process_links(self, links):
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [
link for link in links if _matches(link.url, self.allow_res)
]
if self.deny_res:
links = [
link for link in links if not _matches(link.url, self.deny_res)
]
if self.allow_domains:
links = [
link for link in links
if url_is_from_any_domain(link.url, self.allow_domains)
]
if self.deny_domains:
links = [
link for link in links
if not url_is_from_any_domain(link.url, self.deny_domains)
]
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = BaseSgmlLinkExtractor._process_links(self, links)
return links
def extract_links(self, response):
if self.restrict_xpaths:
hxs = HtmlXPathSelector(response)
html_slice = ''.join(''.join(html_fragm for html_fragm in hxs.select(xpath_expr).extract()) \
for xpath_expr in self.restrict_xpaths)
links = self._extract_links(html_slice, response.url, response.encoding)
else:
links = BaseSgmlLinkExtractor.extract_links(self, response)
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [link for link in links if _matches(link.url, self.allow_res)]
if self.deny_res:
links = [link for link in links if not _matches(link.url, self.deny_res)]
if self.allow_domains:
links = [link for link in links if url_is_from_any_domain(link.url, self.allow_domains)]
if self.deny_domains:
links = [link for link in links if not url_is_from_any_domain(link.url, self.deny_domains)]
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
return links
def _process_links(self, links):
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [link for link in links if _matches(link.url, self.allow_res)]
if self.deny_res:
links = [link for link in links if not _matches(link.url, self.deny_res)]
if self.allow_domains:
links = [link for link in links if url_is_from_any_domain(link.url, self.allow_domains)]
if self.deny_domains:
links = [link for link in links if not url_is_from_any_domain(link.url, self.deny_domains)]
new_links = []
for link in links:
CustomerId = link.url.split('/')[6]
if not self._ignore_identifier(CustomerId):
log.msg("Found CustomerId: "+CustomerId,level=log.DEBUG)
new_links.append(link)
links = new_links
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = BaseSgmlLinkExtractor._process_links(self, links)
return links
def _link_allowed(self, link):
if not _is_valid_url(link.url):
# 非法url
return False
if self.allow_res and not _matches(link.url, self.allow_res):
# 不再允许规则里面
return False
if self.deny_res and _matches(link.url, self.deny_res):
# 在拒绝规则里面
return False
# 解析url
parsed_url = urlparse(link.url)
if self.allow_domains and not url_is_from_any_domain(
parsed_url, self.allow_domains):
# 不再允许域名里面
return False
if self.deny_domains and url_is_from_any_domain(
parsed_url, self.deny_domains):
# 在拒绝域名里面
return False
if self.deny_extensions and url_has_any_extension(
parsed_url, self.deny_extensions):
# 在拒绝后缀名里面
return False
# 可以
return True
def _link_allowed(self, link):
_matches = lambda url, regexs: any(r.search(url) for r in regexs)
_is_valid_url = lambda url: url.split('://', 1)[
0] in {'http', 'https', 'file', 'ftp'}
if not _is_valid_url(link.url):
self.logger.warning(f"Not allowed: {link.url} // no valid url")
return False
if self.allow_res and not _matches(link.url, self.allow_res):
self.logger.warning(
f"Not allowed: {link.url} // does not match whitelist")
return False
if self.deny_res and _matches(link.url, self.deny_res):
self.logger.warning(
f"Not allowed: {link.url} // matches blacklist")
return False
parsed_url = urlparse(link.url)
if self.allow_domains and not url_is_from_any_domain(
parsed_url, self.allow_domains):
self.logger.warning(
f"Not allowed: {link.url} // domain not listed as allowed")
return False
if self.deny_domains and url_is_from_any_domain(
parsed_url, self.deny_domains):
self.logger.warning(
f"Not allowed: {link.url} // domain is listed as denied")
return False
if self.deny_extensions and url_has_any_extension(
parsed_url, self.deny_extensions):
self.logger.warning(
f"Not allowed: {link.url} // extension is denied")
return False
if self.restrict_text and not _matches(link.text, self.restrict_text):
return False
return True
def _process_links(self, links):
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [link for link in links if _matches(link.url, self.allow_res)]
if self.deny_res:
links = [link for link in links if not _matches(link.url, self.deny_res)]
if self.allow_domains:
links = [link for link in links if url_is_from_any_domain(link.url, self.allow_domains)]
if self.deny_domains:
links = [link for link in links if not url_is_from_any_domain(link.url, self.deny_domains)]
new_links = []
for link in links:
ASIN = link.url.split('/')[5]
if not self._ignore_identifier(ASIN):
log.msg("Found ASIN: "+ASIN,level=log.DEBUG)
link.url = "http://www.amazon.com/product-reviews/"+ASIN+"/ref%3Ddp_top_cm_cr_acr_txt?ie=UTF8&showViewpoints=0"
new_links.append(link)
links = new_links
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = BaseSgmlLinkExtractor._process_links(self, links)
return links
def matches(self, url):
if self.allow_domains and not url_is_from_any_domain(url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(url, self.deny_domains):
return False
allowed = [regex.search(url) for regex in self.allow_res] if self.allow_res else [True]
denied = [regex.search(url) for regex in self.deny_res] if self.deny_res else []
return any(allowed) and not any(denied)
def matches(self, url):
if self.allow_domains and not url_is_from_any_domain(url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(url, self.deny_domains):
return False
allowed = [regex.search(url) for regex in self.allow_res] if self.allow_res else [True]
denied = [regex.search(url) for regex in self.deny_res] if self.deny_res else []
return any(allowed) and not any(denied)
def __call__(self, requests):
"""Filter domains"""
processed = (req for req in requests)
if self.allow:
processed = (req for req in requests
if url_is_from_any_domain(req.url, self.allow))
if self.deny:
processed = (req for req in requests
if not url_is_from_any_domain(req.url, self.deny))
return processed
def __call__(self, requests):
"""Filter domains"""
processed = (req for req in requests)
if self.allow:
processed = (req for req in requests
if url_is_from_any_domain(req.url, self.allow))
if self.deny:
processed = (req for req in requests
if not url_is_from_any_domain(req.url, self.deny))
return processed
def _link_allowed(self, link):
if not _is_valid_url(link.url):
return False
if self.allow_res and not _matches(link.url, self.allow_res):
return False
if self.deny_res and _matches(link.url, self.deny_res):
return False
parsed_url = urlparse(link.url)
if self.allow_domains and not url_is_from_any_domain(parsed_url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(parsed_url, self.deny_domains):
return False
if self.deny_extensions and url_has_any_extension(parsed_url, self.deny_extensions):
return False
return True
def _link_allowed(self, link):
if not _is_valid_url(link.url):
return False
if self.allow_res and not _matches(link.url, self.allow_res):
return False
if self.deny_res and _matches(link.url, self.deny_res):
return False
parsed_url = urlparse(link.url)
if self.allow_domains and not url_is_from_any_domain(parsed_url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(parsed_url, self.deny_domains):
return False
if self.deny_extensions and url_has_any_extension(parsed_url, self.deny_extensions):
return False
return True
def _link_allowed(self, link):
parsed_url = urlparse(link.url)
allowed = _is_valid_url(link.url)
if self.allow_res:
allowed &= _matches(link.url, self.allow_res)
if self.deny_res:
allowed &= not _matches(link.url, self.deny_res)
if self.allow_domains:
allowed &= url_is_from_any_domain(parsed_url, self.allow_domains)
if self.deny_domains:
allowed &= not url_is_from_any_domain(parsed_url, self.deny_domains)
if self.deny_extensions:
allowed &= not url_has_any_extension(parsed_url, self.deny_extensions)
if allowed and self.canonicalize:
link.url = canonicalize_url(parsed_url)
return allowed
def _link_allowed(self, link):
parsed_url = urlparse(link.url)
allowed = _is_valid_url(link.url)
if self.allow_res:
allowed &= _matches(link.url, self.allow_res)
if self.deny_res:
allowed &= not _matches(link.url, self.deny_res)
if self.allow_domains:
allowed &= url_is_from_any_domain(parsed_url, self.allow_domains)
if self.deny_domains:
allowed &= not url_is_from_any_domain(parsed_url, self.deny_domains)
if self.deny_extensions:
allowed &= not url_has_any_extension(parsed_url, self.deny_extensions)
if allowed and self.canonicalize:
link.url = canonicalize_url(parsed_url)
return allowed
def process_spider_output(self, response, result, spider):
for r in result:
if not isinstance(r, Request):
yield r
continue
feed_url = r.meta.get('feed_url')
if not feed_url or url_is_from_any_domain(feed_url, self.domains):
yield r
def filter_by_domains(ls, exclude=False):
domains = []
for key, op, val in ls:
if key != 'domain' or op != 'under':
log.warning(f'Unknown filter {key} {op}')
continue
domains.append(val)
return lambda u: url_is_from_any_domain(u, domains) ^ exclude
def _process_links(self, links):
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [link for link in links if _matches(link.url, self.allow_res)]
if self.deny_res:
links = [link for link in links if not _matches(link.url, self.deny_res)]
if self.allow_domains:
links = [link for link in links if url_is_from_any_domain(link.url, self.allow_domains)]
if self.deny_domains:
links = [link for link in links if not url_is_from_any_domain(link.url, self.deny_domains)]
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = BaseSgmlLinkExtractor._process_links(self, links)
return links
def matches(self, url):
if self.allow_domains and not url_is_from_any_domain(url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(url, self.deny_domains):
return False
if self.allow_res:
allowed = qualified_range_match(url, self.allow_res, self.allow_range)
else:
allowed = True
if self.deny_res:
denied = qualified_range_match(url, self.deny_res, self.deny_range)
else:
denied = False
print "matches(%s) allowed=%s, denied=%s" % (url, allowed, denied)
return allowed and not denied
def process_request(self, request, spider):
auth = getattr(self, 'auth', None)
if auth and b'Authorization' not in request.headers:
domain = urlparse_cached(request).hostname
if self.domain_unset:
self.domain = domain
self.domain_unset = False
if not self.domain or url_is_from_any_domain(
request.url, [self.domain]):
request.headers[b'Authorization'] = auth
def test_url_is_from_any_domain(self):
url = "http://www.wheele-bin-art.co.uk/get/product/123"
self.assertTrue(url_is_from_any_domain(url, ["wheele-bin-art.co.uk"]))
self.assertFalse(url_is_from_any_domain(url, ["art.co.uk"]))
url = "http://wheele-bin-art.co.uk/get/product/123"
self.assertTrue(url_is_from_any_domain(url, ["wheele-bin-art.co.uk"]))
self.assertFalse(url_is_from_any_domain(url, ["art.co.uk"]))
url = "http://www.Wheele-Bin-Art.co.uk/get/product/123"
self.assertTrue(url_is_from_any_domain(url, ["wheele-bin-art.CO.UK"]))
self.assertTrue(url_is_from_any_domain(url, ["WHEELE-BIN-ART.CO.UK"]))
url = "http://192.169.0.15:8080/mypage.html"
self.assertTrue(url_is_from_any_domain(url, ["192.169.0.15:8080"]))
self.assertFalse(url_is_from_any_domain(url, ["192.169.0.15"]))
url = "javascript:%20document.orderform_2581_1190810811.mode.value=%27add%27;%20javascript:%20document.orderform_2581_1190810811.submit%28%29"
self.assertFalse(url_is_from_any_domain(url, ["testdomain.com"]))
self.assertFalse(url_is_from_any_domain(url + ".testdomain.com", ["testdomain.com"]))
def test_url_is_from_any_domain(self):
url = 'http://www.wheele-bin-art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.co.uk']))
self.assertFalse(url_is_from_any_domain(url, ['art.co.uk']))
url = 'http://wheele-bin-art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.co.uk']))
self.assertFalse(url_is_from_any_domain(url, ['art.co.uk']))
url = 'http://www.Wheele-Bin-Art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.CO.UK']))
self.assertTrue(url_is_from_any_domain(url, ['WHEELE-BIN-ART.CO.UK']))
url = 'http://192.169.0.15:8080/mypage.html'
self.assertTrue(url_is_from_any_domain(url, ['192.169.0.15:8080']))
self.assertFalse(url_is_from_any_domain(url, ['192.169.0.15']))
url = 'javascript:%20document.orderform_2581_1190810811.mode.value=%27add%27;%20javascript:%20document.orderform_2581_1190810811.submit%28%29'
self.assertFalse(url_is_from_any_domain(url, ['testdomain.com']))
self.assertFalse(url_is_from_any_domain(url+'.testdomain.com', ['testdomain.com']))
def matches(self, url):
if self.allow_domains and not url_is_from_any_domain(
url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(
url, self.deny_domains):
return False
if self.allow_res:
allowed = qualified_range_match(url, self.allow_res,
self.allow_range)
else:
allowed = True
if self.deny_res:
denied = qualified_range_match(url, self.deny_res, self.deny_range)
else:
denied = False
print "matches(%s) allowed=%s, denied=%s" % (url, allowed, denied)
return allowed and not denied
def _link_allowed(self, link):
if not _is_valid_url(link.url): #检查 http等前缀
return False
if self.allow_res and not _matches(
link.url, self.allow_res): # 如果有 allow 参数 则判断是否不在 其中
return False
if self.deny_res and _matches(link.url, self.deny_res): #同上 判断是否在deny中
return False
parsed_url = urlparse(link.url) #解析出正确的 url格式的url
if self.allow_domains and not url_is_from_any_domain(
parsed_url, self.allow_domains): #是否不在 allow_domains 中
return False
if self.deny_domains and url_is_from_any_domain(
parsed_url, self.deny_domains): #是否在deny_domains里
return False
if self.deny_extensions and url_has_any_extension(
parsed_url, self.deny_extensions): #是否在忽略扩展名里
return False
if self.restrict_text and not _matches(
link.text, self.restrict_text): #是否在restrict_text里面
return False
return True
def _process_links(self, links):
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [
link for link in links if _matches(link.url, self.allow_res)
]
if self.deny_res:
links = [
link for link in links if not _matches(link.url, self.deny_res)
]
if self.allow_domains:
links = [
link for link in links
if url_is_from_any_domain(link.url, self.allow_domains)
]
if self.deny_domains:
links = [
link for link in links
if not url_is_from_any_domain(link.url, self.deny_domains)
]
new_links = []
for link in links:
ASIN = link.url.split('/')[5]
if not self._ignore_identifier(ASIN):
log.msg("Found ASIN: " + ASIN, level=log.DEBUG)
link.url = "http://www.amazon.com/product-reviews/" + ASIN + "/ref%3Ddp_top_cm_cr_acr_txt?ie=UTF8&showViewpoints=0"
new_links.append(link)
links = new_links
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = BaseSgmlLinkExtractor._process_links(self, links)
return links
def _process_links(self, links):
links = [link for link in links if _is_valid_url(link.url)]
if self.allow_res:
links = [
link for link in links if _matches(link.url, self.allow_res)
]
if self.deny_res:
links = [
link for link in links if not _matches(link.url, self.deny_res)
]
if self.allow_domains:
links = [
link for link in links
if url_is_from_any_domain(link.url, self.allow_domains)
]
if self.deny_domains:
links = [
link for link in links
if not url_is_from_any_domain(link.url, self.deny_domains)
]
new_links = []
for link in links:
CustomerId = link.url.split('/')[6]
if not self._ignore_identifier(CustomerId):
log.msg("Found CustomerId: " + CustomerId, level=log.DEBUG)
new_links.append(link)
links = new_links
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = BaseSgmlLinkExtractor._process_links(self, links)
return links
def parse_item(self, response):
# Don't log redirects
if response.status >= 300 and response.status < 400:
return None
if not url_is_from_any_domain(response.url, self.allowed_domains):
return None
self.scraped_urls.add(response.url.rstrip('/'))
l = len(self.scraped_urls)
if l % 100 == 0:
self.log("%s URLs scraped" % (l,), level=log.INFO)
if l >= self.limit:
raise CloseSpider('page_limit')
def test_url_is_from_any_domain(self):
url = 'http://www.wheele-bin-art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.co.uk']))
self.assertFalse(url_is_from_any_domain(url, ['art.co.uk']))
url = 'http://wheele-bin-art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.co.uk']))
self.assertFalse(url_is_from_any_domain(url, ['art.co.uk']))
url = 'javascript:%20document.orderform_2581_1190810811.mode.value=%27add%27;%20javascript:%20document.orderform_2581_1190810811.submit%28%29'
self.assertFalse(url_is_from_any_domain(url, ['testdomain.com']))
self.assertFalse(url_is_from_any_domain(url+'.testdomain.com', ['testdomain.com']))
def test_url_is_from_any_domain(self):
url = 'http://www.wheele-bin-art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.co.uk']))
self.assertFalse(url_is_from_any_domain(url, ['art.co.uk']))
url = 'http://wheele-bin-art.co.uk/get/product/123'
self.assertTrue(url_is_from_any_domain(url, ['wheele-bin-art.co.uk']))
self.assertFalse(url_is_from_any_domain(url, ['art.co.uk']))
url = 'javascript:%20document.orderform_2581_1190810811.mode.value=%27add%27;%20javascript:%20document.orderform_2581_1190810811.submit%28%29'
self.assertFalse(url_is_from_any_domain(url, ['testdomain.com']))
self.assertFalse(url_is_from_any_domain(url+'.testdomain.com', ['testdomain.com']))
def test_url_is_from_any_domain(self):
url = "http://www.wheele-bin-art.co.uk/get/product/123"
self.assertTrue(url_is_from_any_domain(url, ["wheele-bin-art.co.uk"]))
self.assertFalse(url_is_from_any_domain(url, ["art.co.uk"]))
url = "http://wheele-bin-art.co.uk/get/product/123"
self.assertTrue(url_is_from_any_domain(url, ["wheele-bin-art.co.uk"]))
self.assertFalse(url_is_from_any_domain(url, ["art.co.uk"]))
url = "javascript:%20document.orderform_2581_1190810811.mode.value=%27add%27;%20javascript:%20document.orderform_2581_1190810811.submit%28%29"
self.assertFalse(url_is_from_any_domain(url, ["testdomain.com"]))
self.assertFalse(url_is_from_any_domain(url + ".testdomain.com", ["testdomain.com"]))
def _check_link_domains(self, parsed_url, allow_domains, deny_domains):
if allow_domains and not url_is_from_any_domain(parsed_url, allow_domains):
return False
if deny_domains and url_is_from_any_domain(parsed_url, deny_domains):
return False
return True