lib/utils/crawler.py · javaalpha/sqlmap

代码拉取完成,页面将自动刷新

扫描微信二维码支付

取消

支付完成

richgiteeai

Watch

不关注关注所有动态仅关注版本发行动态关注但不提醒动态

1 Star 0 Fork 1

javaalpha/sqlmap

forked from yeqingchen1/sqlmap

代码 Issues 0 Pull Requests 0 Wiki 统计流水线

服务

加入 Gitee

与超过 1400万开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)

免费加入

已有帐号? 立即登录

文件

master

分支 (2)

标签 (53)

管理

master

gh-pages

1.3.8

1.3.7

1.3.6

1.3.5

1.3.4

1.3.3

1.3.2

1.3

1.2.12

1.2.11

1.2.10

1.2.9

1.2.8

1.2.7

1.2.6

1.2.5

1.2.4

1.2.3

1.2.2

1.2

克隆/下载

HTTPS SSH SVN SVN+SSH 下载ZIP

提示

下载代码请复制以下命令到终端执行

为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName 
git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥中

在 Gitee 上使用 SVN,请访问使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议配置并使用私人令牌替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

分支 2

标签 53

sqlmap

lib

utils

crawler.py

crawler.py 8.94 KB

#!/usr/bin/env python

"""
Copyright (c) 2006-2019 sqlmap developers (http://sqlmap.org/)
See the file 'LICENSE' for copying permission
"""

from __future__ import division

import os
import re
import tempfile
import time

from lib.core.common import checkSameHost
from lib.core.common import clearConsoleLine
from lib.core.common import dataToStdout
from lib.core.common import findPageForms
from lib.core.common import getSafeExString
from lib.core.common import openFile
from lib.core.common import readInput
from lib.core.common import safeCSValue
from lib.core.common import urldecode
from lib.core.compat import xrange
from lib.core.convert import htmlUnescape
from lib.core.data import conf
from lib.core.data import kb
from lib.core.data import logger
from lib.core.datatype import OrderedSet
from lib.core.enums import MKSTEMP_PREFIX
from lib.core.exception import SqlmapConnectionException
from lib.core.exception import SqlmapSyntaxException
from lib.core.settings import CRAWL_EXCLUDE_EXTENSIONS
from lib.core.threads import getCurrentThreadData
from lib.core.threads import runThreads
from lib.parse.sitemap import parseSitemap
from lib.request.connect import Connect as Request
from thirdparty import six
from thirdparty.beautifulsoup.beautifulsoup import BeautifulSoup
from thirdparty.six.moves import http_client as _http_client
from thirdparty.six.moves import urllib as _urllib

def crawl(target):
 try:
 visited = set()
 threadData = getCurrentThreadData()
 threadData.shared.value = OrderedSet()

def crawlThread():
 threadData = getCurrentThreadData()

while kb.threadContinue:
 with kb.locks.limit:
 if threadData.shared.unprocessed:
 current = threadData.shared.unprocessed.pop()
 if current in visited:
 continue
 elif conf.crawlExclude and re.search(conf.crawlExclude, current):
 dbgMsg = "skipping '%s'" % current
 logger.debug(dbgMsg)
 continue
 else:
 visited.add(current)
 else:
 break

content = None
 try:
 if current:
 content = Request.getPage(url=current, crawling=True, raise404=False)[0]
 except SqlmapConnectionException as ex:
 errMsg = "connection exception detected ('%s'). skipping " % getSafeExString(ex)
 errMsg += "URL '%s'" % current
 logger.critical(errMsg)
 except SqlmapSyntaxException:
 errMsg = "invalid URL detected. skipping '%s'" % current
 logger.critical(errMsg)
 except _http_client.InvalidURL as ex:
 errMsg = "invalid URL detected ('%s'). skipping " % getSafeExString(ex)
 errMsg += "URL '%s'" % current
 logger.critical(errMsg)

if not kb.threadContinue:
 break

if isinstance(content, six.text_type):
 try:
 match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
 if match:
 content = "<html>%s</html>" % match.group(1)

soup = BeautifulSoup(content)
 tags = soup('a')

tags += re.finditer(r'(?i)<a[^>]+href=["\'](?P<href>[^>"\']+)', content)

for tag in tags:
 href = tag.get("href") if hasattr(tag, "get") else tag.group("href")

if href:
 if threadData.lastRedirectURL and threadData.lastRedirectURL[0] == threadData.lastRequestUID:
 current = threadData.lastRedirectURL[1]
 url = _urllib.parse.urljoin(current, htmlUnescape(href))

# flag to know if we are dealing with the same target host
 _ = checkSameHost(url, target)

if conf.scope:
 if not re.search(conf.scope, url, re.I):
 continue
 elif not _:
 continue

if url.split('.')[-1].lower() not in CRAWL_EXCLUDE_EXTENSIONS:
 with kb.locks.value:
 threadData.shared.deeper.add(url)
 if re.search(r"(.*?)\?(.+)", url):
 threadData.shared.value.add(url)
 except UnicodeEncodeError: # for non-HTML files
 pass
 except ValueError: # for non-valid links
 pass
 finally:
 if conf.forms:
 findPageForms(content, current, False, True)

if conf.verbose in (1, 2):
 threadData.shared.count += 1
 status = '%d/%d links visited (%d%%)' % (threadData.shared.count, threadData.shared.length, round(100.0 * threadData.shared.count / threadData.shared.length))
 dataToStdout("\r[%s] [INFO] %s" % (time.strftime("%X"), status), True)

threadData.shared.deeper = set()
 threadData.shared.unprocessed = set([target])

if not conf.sitemapUrl:
 message = "do you want to check for the existence of "
 message += "site's sitemap(.xml) [y/N] "

if readInput(message, default='N', boolean=True):
 found = True
 items = None
 url = _urllib.parse.urljoin(target, "/sitemap.xml")
 try:
 items = parseSitemap(url)
 except SqlmapConnectionException as ex:
 if "page not found" in getSafeExString(ex):
 found = False
 logger.warn("'sitemap.xml' not found")
 except:
 pass
 finally:
 if found:
 if items:
 for item in items:
 if re.search(r"(.*?)\?(.+)", item):
 threadData.shared.value.add(item)
 if conf.crawlDepth > 1:
 threadData.shared.unprocessed.update(items)
 logger.info("%s links found" % ("no" if not items else len(items)))

infoMsg = "starting crawler"
 if conf.bulkFile:
 infoMsg += " for target URL '%s'" % target
 logger.info(infoMsg)

for i in xrange(conf.crawlDepth):
 threadData.shared.count = 0
 threadData.shared.length = len(threadData.shared.unprocessed)
 numThreads = min(conf.threads, len(threadData.shared.unprocessed))

if not conf.bulkFile:
 logger.info("searching for links with depth %d" % (i + 1))

runThreads(numThreads, crawlThread, threadChoice=(i > 0))
 clearConsoleLine(True)

if threadData.shared.deeper:
 threadData.shared.unprocessed = set(threadData.shared.deeper)
 else:
 break

except KeyboardInterrupt:
 warnMsg = "user aborted during crawling. sqlmap "
 warnMsg += "will use partial list"
 logger.warn(warnMsg)

finally:
 clearConsoleLine(True)

if not threadData.shared.value:
 warnMsg = "no usable links found (with GET parameters)"
 logger.warn(warnMsg)
 else:
 for url in threadData.shared.value:
 kb.targets.add((urldecode(url, kb.pageEncoding), None, None, None, None))

storeResultsToFile(kb.targets)

def storeResultsToFile(results):
 if not results:
 return

if kb.storeCrawlingChoice is None:
 message = "do you want to store crawling results to a temporary file "
 message += "for eventual further processing with other tools [y/N] "

kb.storeCrawlingChoice = readInput(message, default='N', boolean=True)

if kb.storeCrawlingChoice:
 handle, filename = tempfile.mkstemp(prefix=MKSTEMP_PREFIX.CRAWLER, suffix=".csv" if conf.forms else ".txt")
 os.close(handle)

infoMsg = "writing crawling results to a temporary file '%s' " % filename
 logger.info(infoMsg)

with openFile(filename, "w+b") as f:
 if conf.forms:
 f.write("URL,POST\n")

for url, _, data, _, _ in results:
 if conf.forms:
 f.write("%s,%s\n" % (safeCSValue(url), safeCSValue(data or "")))
 else:
 f.write("%s\n" % url)

一键复制编辑原始数据按行查看历史

Miroslav Stampar 提交于 2019年08月20日 06:22 +08:00 . Fixes #3883

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224

#!/usr/bin/env python

"""
Copyright (c) 2006-2019 sqlmap developers (http://sqlmap.org/)
See the file 'LICENSE' for copying permission
"""

from __future__ import division

import os
import re
import tempfile
import time

from lib.core.common import checkSameHost
from lib.core.common import clearConsoleLine
from lib.core.common import dataToStdout
from lib.core.common import findPageForms
from lib.core.common import getSafeExString
from lib.core.common import openFile
from lib.core.common import readInput
from lib.core.common import safeCSValue
from lib.core.common import urldecode
from lib.core.compat import xrange
from lib.core.convert import htmlUnescape
from lib.core.data import conf
from lib.core.data import kb
from lib.core.data import logger
from lib.core.datatype import OrderedSet
from lib.core.enums import MKSTEMP_PREFIX
from lib.core.exception import SqlmapConnectionException
from lib.core.exception import SqlmapSyntaxException
from lib.core.settings import CRAWL_EXCLUDE_EXTENSIONS
from lib.core.threads import getCurrentThreadData
from lib.core.threads import runThreads
from lib.parse.sitemap import parseSitemap
from lib.request.connect import Connect as Request
from thirdparty import six
from thirdparty.beautifulsoup.beautifulsoup import BeautifulSoup
from thirdparty.six.moves import http_client as _http_client
from thirdparty.six.moves import urllib as _urllib

def crawl(target):
 try:
 visited = set()
 threadData = getCurrentThreadData()
 threadData.shared.value = OrderedSet()

 def crawlThread():
 threadData = getCurrentThreadData()

 while kb.threadContinue:
 with kb.locks.limit:
 if threadData.shared.unprocessed:
 current = threadData.shared.unprocessed.pop()
 if current in visited:
 continue
 elif conf.crawlExclude and re.search(conf.crawlExclude, current):
 dbgMsg = "skipping '%s'" % current
 logger.debug(dbgMsg)
 continue
 else:
 visited.add(current)
 else:
 break

 content = None
 try:
 if current:
 content = Request.getPage(url=current, crawling=True, raise404=False)[0]
 except SqlmapConnectionException as ex:
 errMsg = "connection exception detected ('%s'). skipping " % getSafeExString(ex)
 errMsg += "URL '%s'" % current
 logger.critical(errMsg)
 except SqlmapSyntaxException:
 errMsg = "invalid URL detected. skipping '%s'" % current
 logger.critical(errMsg)
 except _http_client.InvalidURL as ex:
 errMsg = "invalid URL detected ('%s'). skipping " % getSafeExString(ex)
 errMsg += "URL '%s'" % current
 logger.critical(errMsg)

 if not kb.threadContinue:
 break

 if isinstance(content, six.text_type):
 try:
 match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
 if match:
 content = "<html>%s</html>" % match.group(1)

 soup = BeautifulSoup(content)
 tags = soup('a')

 tags += re.finditer(r'(?i)<a[^>]+href=["\'](?P<href>[^>"\']+)', content)

 for tag in tags:
 href = tag.get("href") if hasattr(tag, "get") else tag.group("href")

 if href:
 if threadData.lastRedirectURL and threadData.lastRedirectURL[0] == threadData.lastRequestUID:
 current = threadData.lastRedirectURL[1]
 url = _urllib.parse.urljoin(current, htmlUnescape(href))

 # flag to know if we are dealing with the same target host
 _ = checkSameHost(url, target)

 if conf.scope:
 if not re.search(conf.scope, url, re.I):
 continue
 elif not _:
 continue

 if url.split('.')[-1].lower() not in CRAWL_EXCLUDE_EXTENSIONS:
 with kb.locks.value:
 threadData.shared.deeper.add(url)
 if re.search(r"(.*?)\?(.+)", url):
 threadData.shared.value.add(url)
 except UnicodeEncodeError: # for non-HTML files
 pass
 except ValueError: # for non-valid links
 pass
 finally:
 if conf.forms:
 findPageForms(content, current, False, True)

 if conf.verbose in (1, 2):
 threadData.shared.count += 1
 status = '%d/%d links visited (%d%%)' % (threadData.shared.count, threadData.shared.length, round(100.0 * threadData.shared.count / threadData.shared.length))
 dataToStdout("\r[%s] [INFO] %s" % (time.strftime("%X"), status), True)

 threadData.shared.deeper = set()
 threadData.shared.unprocessed = set([target])

 if not conf.sitemapUrl:
 message = "do you want to check for the existence of "
 message += "site's sitemap(.xml) [y/N] "

 if readInput(message, default='N', boolean=True):
 found = True
 items = None
 url = _urllib.parse.urljoin(target, "/sitemap.xml")
 try:
 items = parseSitemap(url)
 except SqlmapConnectionException as ex:
 if "page not found" in getSafeExString(ex):
 found = False
 logger.warn("'sitemap.xml' not found")
 except:
 pass
 finally:
 if found:
 if items:
 for item in items:
 if re.search(r"(.*?)\?(.+)", item):
 threadData.shared.value.add(item)
 if conf.crawlDepth > 1:
 threadData.shared.unprocessed.update(items)
 logger.info("%s links found" % ("no" if not items else len(items)))

 infoMsg = "starting crawler"
 if conf.bulkFile:
 infoMsg += " for target URL '%s'" % target
 logger.info(infoMsg)

 for i in xrange(conf.crawlDepth):
 threadData.shared.count = 0
 threadData.shared.length = len(threadData.shared.unprocessed)
 numThreads = min(conf.threads, len(threadData.shared.unprocessed))

 if not conf.bulkFile:
 logger.info("searching for links with depth %d" % (i + 1))

 runThreads(numThreads, crawlThread, threadChoice=(i > 0))
 clearConsoleLine(True)

 if threadData.shared.deeper:
 threadData.shared.unprocessed = set(threadData.shared.deeper)
 else:
 break

 except KeyboardInterrupt:
 warnMsg = "user aborted during crawling. sqlmap "
 warnMsg += "will use partial list"
 logger.warn(warnMsg)

 finally:
 clearConsoleLine(True)

 if not threadData.shared.value:
 warnMsg = "no usable links found (with GET parameters)"
 logger.warn(warnMsg)
 else:
 for url in threadData.shared.value:
 kb.targets.add((urldecode(url, kb.pageEncoding), None, None, None, None))

 storeResultsToFile(kb.targets)

def storeResultsToFile(results):
 if not results:
 return

 if kb.storeCrawlingChoice is None:
 message = "do you want to store crawling results to a temporary file "
 message += "for eventual further processing with other tools [y/N] "

 kb.storeCrawlingChoice = readInput(message, default='N', boolean=True)

 if kb.storeCrawlingChoice:
 handle, filename = tempfile.mkstemp(prefix=MKSTEMP_PREFIX.CRAWLER, suffix=".csv" if conf.forms else ".txt")
 os.close(handle)

 infoMsg = "writing crawling results to a temporary file '%s' " % filename
 logger.info(infoMsg)

 with openFile(filename, "w+b") as f:
 if conf.forms:
 f.write("URL,POST\n")

 for url, _, data, _, _ in results:
 if conf.forms:
 f.write("%s,%s\n" % (safeCSValue(url), safeCSValue(data or "")))
 else:
 f.write("%s\n" % url)