def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
try:
print '[+] Printing Links From Regex.'
link_finder = re.compile('href="(.*?)"')
links = link_finder.findall(html)
for link in links:
print link
except:
pass
try:
print '\n[+] Printing Links From BeautifulSoup.'
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print link['href']
except:
pass
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url, 'rb')
html = page.read()
try:
print('==========================================')
print('[+] Printing Links From Regex.')
link_finder = re.compile('href="(.*?)"')
links = link_finder.findall(str(html, encoding='UTF-8'))
print(type(links))
for link in links:
print(link)
except Exception as e:
print("re find error: " + e)
pass
try:
print('===========================================')
print('\n[+] Printing Links From BeautifulSoup.')
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print(link['href'])
except Exception as e:
print("re find error: " + e)
pass
def print_links(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
try:
print("[+] Printing Links From Regex.")
link_finder = re.compile('href="(.*?)"')
print("---isshe----1---")
links = link_finder.findall(html) #str(html))
print("---isshe----2---")
for link in links:
print(link)
except Exception as e:
print("Unexpected error:", e) #sys.exc_info()[0])
exit(0)
try:
print("\n[+] Printing Links From BeautifulSoup.")
soup = BeautifulSoup(str(html), features="html5lib")
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print(link["href"])
except:
print("Unexpected error:", sys.exc_info()[0])
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
try:
print('[+] Printing Links From Regex.')
link_finder = re.compile('href="(.*?)"')
links = link_finder.findall(html)
for link in links:
print(link)
except:
pass
try:
print('\n[+] Printing Links From BeautifulSoup.')
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if 'href' in link:
print(link['href'])
except:
pass
def google(search_term):
ab = anonBrowser()
search_term = urllib.parse.quote_plus(search_term)
response = ab.open('http://ajax.googleapis.com/'+\
'ajax/services/search/web?v=1.0&q='+ search_term)
print(response.text)
def google(search_term):
ab = anonBrowser()
search_term = urllib.quote_plus(search_term)
response = ab.open('http://ajax.googleapis.com/'+\
'ajax/services/search/web?v=1.0&q='+ search_term)
print response.read()
def google(search_term):
ab = anonBrowser()
search_term = urllib.quote_plus(search_term)
response = ab.open('http://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=' + search_term)
objects = json.load(response)
print objects
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
try:
print '[+] printing links from regex'
link_finder = re.compile('href="(.*?)"')
links = link_finder.findall(html)
for link in links:
print link
except:
pass
try:
print '\n[+] printing links from beautifulsoup'
# 아래 명령어로 html 코드를 긁어온다
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print link['href']
except:
pass
def google(search_term):
ab = anonBrowser()
search_term = urllib.parse.quote_plus(search_term)
response = ab.open('https://developers.google.com/custom-search' +
search_term)
objects = response.text
results = []
print(objects)
def google(search_term):
ab = anonBrowser()
search_term = urllib.quote_plus(search_term)
response = ab.open('http://ajax.googleapis.com/'+\
'ajax/services/search/web?v=1.0&q='+ search_term)
objects = json.load(response)
print objects
def google(search_term):
ab = anonBrowser()
# URL编码
search_term = urllib.quote_plus(search_term)
response = ab.open(
'https://www.googleapis.com/customsearch/v1?key=AIzaSyCn_IE6NM_ATjZ0j5vfXIFlyW-EpGs5gsU&cx=006431901905483214390:i3yxhoqkzo0&num=1&alt=json&q='
+ search_term)
objects = json.load(response)
print objects
def get_tweets(handle):
query = urllib.parse.quote_plus('from:' + handle+\
' since:2009-01-01 include:retweets')
tweets = []
browser = anonBrowser()
browser.anonymize()
response = browser.open('http://search.twitter.com/'+\
'search.json?q='+ query)
json_objects = response.text
print(json_objects)
def google(search_term):
ab = anonBrowser()
search_term = urllib.quote_plus(search_term)
response = ab.open('http://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=' + search_term)
objects = json.load(response)
results = []
for result in objects['responseData']['results']:
url = result['url']
title = result['titleNoFormatting']
text = result['content']
new_gr = Google_Result(title, text, url)
results.append(new_gr)
return results
def printLinks(url):
ab=anonBrowser()
ab.anonymize()
page=ab.open(url)
html=page.read()
try:
soup=BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print link['href']
except:
pass
def query_twitter(self, query):
query = urllib.quote_plus(query)
results = []
browser = anonBrowser()
response = browser.open('http://search.twitter.com/search.json?q='+query)
json_objects = json.load(response)
for result in json_objects['results']:
new_result = {}
new_result['from_user'] = result['from_user_name']
new_result['geo'] = result['geo']
result['tweet'] = result['text']
results.append(new_result)
return results
def google(search_term):
ab = anonBrowser()
search_term = urllib.quote_plus(search_term)
response = ab.open('http://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=' + search_term)
objects = json.load(response)
results = []
for result in objects['responseData']['results']:
url = result['url']
title = result['titleNoFormatting']
text = result['content']
new_gr = Google_Result(title, text, url)
results.append(new_gr)
return results
def google(search_term):
ab = anonBrowser()
search_term = urllib.quote_plus(search_term)
response = ab.open("http://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=" + search_term)
objects = json.load(response)
results = []
for result in objects["responseData"]["results"]:
url = result["url"]
title = result["titleNoFormatting"]
text = result["content"]
new_gr = Google_Result(title, text, url)
results.append(new_gr)
return results
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
try:
print 'Printing links from Regex'
link_finder = re.compile('href="(.*?)"')
links = link_finder.findall(html)
for link in links:
print link
except:
pass
def query_twitter(self, query):
query = urllib3.quote_plus(query)
results = []
browser = anonBrowser()
response = browser.open('https://search.twitter.com/search.json?q=' +
query)
json_objects = json.load(response)
for result in json_objects['results']:
new_result = {}
new_result['from_user'] = result['from_user_name']
new_result['geo'] = result['geo']
new_result['tweet'] = result['text']
results.append(new_result)
return results
def get_tweets(self):
query = urllib.quote_plus('from:' + self.handle + ' since:2009-01-01 include:retweets')
tweets = []
browser = anonBrowser()
browser.anonymize()
response = browser.open('http://search.twitter.com' + 'search.json?q=' + query)
json_objects = json.load(response)
for result in json_objects['results']:
new_result = {}
new_result['from_user'] = result['from_user_name']
new_result['geo'] = result['text']
tweets.append(new_result)
return tweets
def get_tweets(self):
query = urllib.quote_plus('from:' + self.handle+' since:2009-01-01 include:retweets')
tweets = []
browser = anonBrowser()
browser.anonymize()
response = browser.open('http://search.twitter.com/'+'search.json?q='+query)
json_objects = json.load(response)
for result in json_objects['results']:
new_result = {}
new_result['from_user'] = result['from_user_name']
new_result['geo'] = result['geo']
new_result['tweet'] = result['text']
tweets.append(new_result)
return tweets
def mirrorImages(url, dir):
ab = anonBrowser()
ab.anonymize()
html = ab.open(url)
soup = BeautifulSoup(html)
image_tags = soup.findall('img')
for image in image_tags:
filename = image['src'].lstrip('https://')
filename = os.path.join(dir, filename.replace('/', '_'))
print('[+] Saving ' + str(filename))
data = ab.open(image['src']).read()
ab.back()
save = open(filename, 'wb')
save.write(data)
save.close()
def mirrorImages(url , dir):
ab=anonBrowser()
ab.anonymize()
html=ab.open(url)
soup=BeautifulSoup(html)
image_tags=soup.findAll('img')
for image in image_tags:
filename=image['src'].lstrip('http://')
filename=os.path.join(dir,filename.replace('/','_'))
print '[+] Saving'+str(filename)
data= ab.open(image['src']).read()
ab.back()
save=open(filename,'wb')
save.write(data)
save.close()
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
try:
print '[+] Printing Links From BeautifulSoup.'
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print link['href']
except:
pass
def mirrorImages(url, dire):
ab = anonBrowser()
ab.anonymize()
html = ab.open(url)
soup = BeautifulSoup(html)
image_tags = soup.findAll("img")
for image in image_tags:
filename = image["src"].lstrip("http://")
filename = os.path.join(dire, filename.replace("/", "_"))
print "[+] Saving " + str(filename)
data = ab.open(image["src"]).read()
ab.back()
save = open(filename, "wb")
save.write(data)
save.close()
def printLinks(url, indent=0, ab=None):
if ab is None:
ab = anonBrowser()
ab.anonymize()
indentation = ""
for i in range(indent):
indentation += " "
try:
page = ab.open(url)
html = page.read()
except:
if not indent:
print '[!!!] Exception. Cannot open page'
return
# try:
# print '[+] Printing Links From Regex.'
# link_finder = re.compile('href="(.*?)"')
# links = link_finder.findall(html)
# for link in links:
# print link
# except:
# pass
file_finder = re.compile('.*\.\w{1,4}$')
try:
if not indent:
print '\n[+] Pring Links from BeautifulSoup'
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
output = link['href']
if '../' in output:
continue
print indentation + output
if len(file_finder.findall(output)):
continue
#if output.endswith('.mkv') or output.endswith('.jpg')\
# or output.endswith('mp4') or output.endswith('png')\
# or output.endswith('jpeg') \
# or output.endswith('avi') \
# or output.endswith('aac'):
# continue
printLinks(url + '/' + output, indent=indent + 1, ab=ab)
except Exception, e:
#print e
pass
def get_tweets(handle):
query = urllib.quote_plus("from:" + handle + " since:2009-01-01 include:retweets")
tweets = []
browser = anonBrowser()
browser.anonymize()
response = browser.open("http://search.twitter.com/" + "search.json?q=" + query)
json_objects = json.load(response)
for result in json_objects["results"]:
new_result = {}
new_result["from_user"] = result["from_user_name"]
new_result["geo"] = result["geo"]
new_result["tweet"] = result["text"]
tweets.append(new_result)
return tweets
def query_twitter(self, query):
query = urllib.parse.quote_plus(query)
results = []
browser = anonBrowser()
response = browser.open(\
'http://search.twitter.com/search.json?q='+ query)
json_objects = response.text
print(json_objects)
# for result in json_objects['results']:
# new_result = {}
# new_result['from_user'] = result['from_user_name']
# new_result['geo'] = result['geo']
# new_result['tweet'] = result['text']
#results.append(new_result)
return results
def mirror_images(url, dir):
ab = anonBrowser()
ab.anonymize()
html = ab.open(url)
soup = BeautifulSoup(html)
image_tags = soup.findAll('img')
for image in image_tags:
filename = image['src'].lstrip('http://')
if not filename:
continue
filename = os.path.join(dir, filename.replace('/', '_'))
print("[+] Saving " + str(filename) + ", src = " + image['src'])
data = ab.open(image['src']).read()
ab.back()
save = open(filename, "wb")
save.write(data)
save.close()
def get_tweets(handle):
query = urllib.parse.quote_plus('from:' + handle+\
' since:2009-01-01 include:retweets')
tweets = []
browser = anonBrowser()
browser.anonymize()
response = browser.open('http://search.twitter.com/'+\
'search.json?q=' + query)
json_objects = response.text
print(json_objects)
# for result in json_objects['results']:
# new_result = {}
# new_result['from_user'] = result['from_user_name']
# new_result['geo'] = result['geo']
# new_result['tweet'] = result['text']
#tweets.append(new_result)
return tweets
def query_twitter(self, query):
try:
query = urllib.parse.quote_plus(query)
results = []
browser = anonBrowser()
print('http://search.twitter.com/search.json?q='+query)
response = browser.open(\
'http://search.twitter.com/search.json?q='+
query, 'rb')
json_objects = json.load(response)
for result in json_objects['results']:
new_result = {}
new_result['from_user'] = result['from_user_name']
new_result['geo'] = result['geo']
new_result['tweet'] = result['text']
results.append(new_result)
except Exception as e:
print(e)
pass
return results
def mirrorImages(url, dir):
ab = anonBrowser()
ab.anonymize()
html = ab.open(url)
soup = BeautifulSoup(html)
# Finds all HTML objects with the img tag
image_tags = soup.findAll('img')
# Downloads the picture and saves it to local hard drive
# as a binary file
for image in image_tags:
filename = image['src'].lstrip('http://')
filename = os.path.join(dir,\
filename.replace('/', '_'))
print '[+] Saving ' + str(filename)
data = ab.open(image['src']).read()
ab.back()
save = open(filename, 'wb')
save.write(data)
save.close()
def google(search_term):
ab = anonBrowser()
# URL编码
search_term = urllib.quote_plus(search_term)
response = ab.open(
'https://www.googleapis.com/customsearch/v1?key=AIzaSyCn_IE6NM_ATjZ0j5vfXIFlyW-EpGs5gsU&cx=006431901905483214390:i3yxhoqkzo0&num=1&alt=json&q='
+ search_term)
objects = json.load(response)
results = []
for result in objects['items']:
url = result['link']
title = result['title']
text = result['snippet']
print url
print title
print text
new_gr = Google_Result(title, text, url)
results.append(new_gr)
return results
def get_tweets(handle):
query = urllib.parse.quote_plus('from:' + handle+\
'&result_type=mixed&count=2')
#' since:2019-01-01 include:retweets')
tweets = []
browser = anonBrowser()
browser.anonymize()
print('https://api.twitter.com/1.1/search/'+\
'tweets.json?q=' + query)
response = browser.open('http://search.twitter.com/1.1/'+\
'search.json?q=' + query)
json_objects = json.load(response)
for result in json_objects['results']:
new_result = {}
new_result['from_user'] = result['from_user_name']
new_result['geo'] = result['geo']
new_result['tweet'] = result['text']
tweets.append(new_result)
return tweets
def fetchHTML(url):
print '[-] HTML fetching started'
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
print '[-] HTML fetching done'
allLinks = fetchLinks(html)
print '[-] HREF parsed'
allScripts = fetchScripts(html)
print '[-] SCRIPT ref parsed'
allMetas = fetchMetadata(html)
print '[-] METADATA parsed'
answer = {}
answer['message'] = 'OK'
answer['links'] = allLinks
answer['scripts'] = allScripts
answer['meta'] = allMetas
print '[+] Returning the results'
return answer
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
# 使用re模块解析href链接
try:
print '[+] Printing Links From Regex.'
link_finder = re.compile('href="(.*?)"')
links = link_finder.findall(html)
for link in links:
print link
except:
pass
# 使用bs4模块解析href链接
try:
print '\n[+] Printing Links From BeautifulSoup.'
soup = BeautifulSoup(html)
links = soup.findAll(name='a')
for link in links:
if link.has_key('href'):
print link['href']
except:
pass
#!/usr/bin/python
# -*- coding: utf-8 -*-
from anonBrowser import *
user_agents=('User-agent','superSecretBroswer')
ab = anonBrowser(user_agents)
for attempt in range(1, 5):
ab.anonymize()
print('[*] Fetching page')
response = ab.open('http://kittenwar.com')
for cookie in ab.cookie_jar:
print(cookie)
from anonBrowser import *
if __name__ == "__main__":
user_agents = [('User-Agent', 'superSecretBroswer')]
ab = anonBrowser(proxies=[], user_agents=user_agents)
for attempt in range(1, 5):
ab.anonymize()
print('[*] Fetching page')
response = ab.open("http://kittenwar.com")
for cookie in ab.cookie_jar:
print(cookie)
from anonBrowser import *
ab = anonBrowser(proxies=[],\
user_agents=[('User-agent','superSecretBroswer')])
for attempt in range(1, 5):
ab.anonymize()
print '[*] Fetching page'
response = ab.open('http://kittenwar.com')
for cookie in ab.cookie_jar:
print cookie
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url)
html = page.read()
def printLinks(url):
ab = anonBrowser()
ab.anonymize()
page = ab.open(url, 'rb')
html = page.read()
print(str(html, encoding='UTF-8'))
#!/usr/bin/python
# -*- coding: utf-8 -*-
from anonBrowser import *
ab = anonBrowser(proxies=[],
user_agents=[('User-agent', 'superSecretBroswer')])
for attempt in range(1, 10):
ab.anonymize()
print '[*] Fetching page'
response = ab.open('http://kittenwar.com')
for cookie in ab.cookie_jar:
print cookie
from anonBrowser import *
ab = anonBrowser(proxies=[], user_agents=['superSecretBroser'])
for attempt in range(1, 5):
ab.anonymize()
response = ab.open('http://www.baidu.com')
for cookie in ab.cookie_jar:
print(cookie)