def test_connection_error(self):
"""Connecting to an unknown domain should raise a ConnectionError"""
with pytest.raises(ConnectionError):
requests.get("http://fooobarbangbazbing.httpbin.org")
with pytest.raises(ConnectionError):
requests.get("http://httpbin.org:1")
def test_status_raising(self):
r = requests.get(httpbin("status", "404"))
with pytest.raises(requests.exceptions.HTTPError):
r.raise_for_status()
r = requests.get(httpbin("status", "500"))
assert not r.ok
def on_aaa_response(self, *args):
message = args[0]
if ('socketid' in message):
self._redis_obj.publish('intercomm', message['socketid'])
self._socketid = message['socketid']
if ('name' in message):
log('O', message['name'])
self._socket_io.emit('send_message', self._executable)
if ('data' in message):
log('O', message['data'])
self._redis_obj.publish('intercomm', '***end***')
if ('picture' in message):
log('D', message['picture'])
file = requests.get(message['picture'])
with open(self._imagepath + '/result' + str(self._socketid) + '.jpg', 'wb') as f:
f.write(file.content)
log('D', 'Image Saved: ' + self._imagepath + '/result' + str(self._socketid) + '.jpg')
if ('mat' in message):
log('D', message['mat'])
file = requests.get(message['mat'])
with open(self._imagepath + '/results' + self._socketid + '.txt', 'wb') as f:
f.write(file.content)
log('D', 'Results Saved: ' + self._imagepath + '/results' + self._socketid + '.txt')
if ('request_data' in message):
self._socket_io.emit('send_message', 'data')
def extract_nearby_cities(item, country):
res = requests.get(item['detail'])
r = res.json()
nearby_cities_url = r['properties']['products']['nearby-cities'][0]['contents']['nearby-cities.json']['url']
res = requests.get(nearby_cities_url)
r = res.json()
out = []
append = out.append
j = 0
for i in r:
city = 'a ' + str(i['distance']) + ' km al '
city += translate_string(i['direction']) + ' de ' + i['name']
city = city.replace(', ' + country, '')
append(city)
j += 1
if j == 3:
break
if len(out) > 1:
out[-1] = 'y ' + out[-1]
nearby_cities = ', '.join(out)
nearby_cities = re.sub(', y', ' y', nearby_cities)
return nearby_cities
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url == None: return sources
year = url['year']
h = {'User-Agent': client.randomagent()}
title = cleantitle.geturl(url['title']).replace('-', '+')
url = urlparse.urljoin(self.base_link, self.search_link % title)
r = requests.get(url, headers=h)
r = BeautifulSoup(r.text, 'html.parser').find('div', {'class': 'item'})
r = r.find('a')['href']
r = requests.get(r, headers=h)
r = BeautifulSoup(r.content, 'html.parser')
quality = r.find('span', {'class': 'calidad2'}).text
url = r.find('div', {'class':'movieplay'}).find('iframe')['src']
if not quality in ['1080p', '720p']:
quality = 'SD'
valid, host = source_utils.is_host_valid(url, hostDict)
sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': False})
return sources
except:
print("Unexpected error in Furk Script: check_api", sys.exc_info()[0])
exc_type, exc_obj, exc_tb = sys.exc_info()
print(exc_type, exc_tb.tb_lineno)
return sources
def test_unicode_get(self):
url = httpbin("/get")
requests.get(url, params={"foo": "føø"})
requests.get(url, params={"føø": "føø"})
requests.get(url, params={"føø": "føø"})
requests.get(url, params={"foo": "foo"})
requests.get(httpbin("ø"), params={"foo": "foo"})
def test_where_3_way_logic(self):
# This column
# ⇓
# ___________________
# | | col1 | col2 |
# -------------------
# | r1 | 1 | | ⇐ This row
# -------------------
# | r2 | 1 | 2 |
# -------------------
response = requests.get(self.dataset_url)
datasets = json.loads(response.content)
self.assertEqual(response.status_code, 200,
msg="Couldn't get the list of datasets")
self.assertEqual(datasets['status']['rowCount'], 2,
msg="2 rows should be in the dataset. r1 and r2")
params = {
"select":'col1',
"where":"'col2' < 2"
}
response = requests.get(self.dataset_url + '/query', params=params)
content = json.loads(response.content)
self.assertEqual(len(content), 0,
msg="The query should have returned no results")
def test_basicauth_with_netrc(self):
auth = ("user", "pass")
wrong_auth = ("wronguser", "wrongpass")
url = httpbin("basic-auth", "user", "pass")
def get_netrc_auth_mock(url):
return auth
requests.sessions.get_netrc_auth = get_netrc_auth_mock
# Should use netrc and work.
r = requests.get(url)
assert r.status_code == 200
# Given auth should override and fail.
r = requests.get(url, auth=wrong_auth)
assert r.status_code == 401
s = requests.session()
# Should use netrc and work.
r = s.get(url)
assert r.status_code == 200
# Given auth should override and fail.
s.auth = wrong_auth
r = s.get(url)
assert r.status_code == 401
def test_connect_timeout(self):
try:
requests.get(TARPIT, timeout=(0.1, None))
assert False, "The connect() request should time out."
except ConnectTimeout as e:
assert isinstance(e, ConnectionError)
assert isinstance(e, Timeout)
def hopcam():
# Should return a list with revmic's dailymotion videos entitled 'yesterday'
yda_uri = 'https://api.dailymotion.com/videos?owners=revmic&' \
'search=yesterday&fields=id,title,description,embed_url,' \
'thumbnail_480_url,views_total'
r = requests.get(yda_uri)
print(r.json())
try:
# Get last item in list in case there are multiples (prev delete failed)
yda_video = get_list(r)[-1]
except IndexError as e:
yda_video = {'title': "Sorry. Couldn't find yesterday's video :'("}
print('IndexError - ', e)
if 'Sorry' in yda_video['title']: # Try again, rummage through all videos
print("trying again")
uri = 'https://api.dailymotion.com/videos?owners=revmic&' \
'fields=id,title,description,embed_url,' \
'thumbnail_480_url,views_total'
videos = get_list(requests.get(uri))
print(videos)
for v in videos:
if v['title'].lower() == 'yesterday':
yda_video = v
return render_template('hopcam.html', yesterday=yda_video)
def get_opendata2_courses():
good_courses = 0
file_name = os.path.join(os.path.realpath(os.path.dirname(__file__)),
'%s/opendata2_departments.json' % c.DEPARTMENTS_DATA_DIR)
with open(file_name) as departments_file:
departments = json.load(departments_file)
# Create a text file for every department
for d in departments:
department = d['subject']
open_data_json = requests.get(
'https://api.uwaterloo.ca/v2/courses/{0}.json?key={1}'.format(
department.upper(), s.OPEN_DATA_API_KEY)).json
open_data_catalog_numbers = []
for course in open_data_json['data']:
open_data_catalog_numbers.append(course['catalog_number'])
# We now poll the individual endpoints of each course for the data
current_dep_json = []
course_url = 'https://api.uwaterloo.ca/v2/courses/{0}/{1}.json?key={2}'
for course in open_data_catalog_numbers:
good_courses += 1
json_data = requests.get(course_url.format(department.upper(),
course, s.OPEN_DATA_API_KEY)).json
current_dep_json.append(json_data['data'])
out_file_name = os.path.join(
os.path.realpath(os.path.dirname(__file__)),
'opendata2_courses/%s.json' % department.lower())
with open(out_file_name, 'w') as courses_out:
json.dump(current_dep_json, courses_out)
print 'Found {num} good courses'.format(num=good_courses)
def get_speakers_ip(self, refresh=False):
""" Get the IP addresses of all the Sonos speakers in the network.
Code contributed by Thomas Bartvig ([email protected])
Arguments:
refresh -- Refresh the speakers IP cache.
Returns:
IP addresses of the Sonos speakers.
"""
if self.speakers_ip and not refresh:
return self.speakers_ip
else:
response = requests.get('http://' + self.speaker_ip +
':1400/status/topology')
text = response.text
grp = re.findall(r'(\d+\.\d+\.\d+\.\d+):1400', text)
for i in grp:
response = requests.get('http://' + i + ':1400/status')
if response.status_code == 200:
self.speakers_ip.append(i)
return self.speakers_ip
def updateCCU(v):
ccuUrl = "http://pi:8080/api/set"
try:
requests.get(ccuUrl + "/AussenTemp/?value=" + str(v.get('outside_temp')))
requests.get(ccuUrl + "/KollectorTemp/?value=" + str(v.get('collector_temp')))
except Exception,e:
logError(e)
def test_small_layer(svc_url, svc_data):
"""
Test a service endpoint to see if the layer is small based on some simple rules.
:param svc_url: The URL pointing to the feature endpoint
:type svc_url: str
:param svc_data: A dictionary containing scraped data from an ESRI feature service endpoint
:type svc_data: dict
:returns: bool -- True if the layer is considered 'small'
"""
# FIXME needs refactoring, better error handling and better logic
global _proxies
try:
if svc_data['geometryType'] in ('esriGeometryPoint', 'esriGeometryMultipoint', 'esriGeometryEnvelope'):
count_query = '/query?where=1%3D1&returnCountOnly=true&f=pjson'
id_query = '/query?where=1%3D1&returnIdsOnly=true&f=json'
r = requests.get(get_base_url(svc_url) + count_query, proxies=_proxies)
if 'count' in r.json():
return r.json()['count'] <= 2000
r = requests.get(get_base_url(svc_url) + id_query, proxies=_proxies)
if 'objectIds' in r.json():
return len(r.json()['objectIds']) <= 2000
except:
pass
return False
def _request_odl_data(self, host, node_connector_list, flow_statistics_list):
# Data to export from OpenDaylight.
data_dict = {}
try:
# Flow table statistics per host (eg. opendaylight, compute, control and neutron)
try:
table_flow_statistics_url = "%s%s%s%s" % (self._odl_inventory_url,'/node/',self.hosts_dict[host],'/table/0/opendaylight-flow-table-statistics:flow-table-statistics')
table_flow_statistics = requests.get(table_flow_statistics_url)
table_flow_statistics.raise_for_status()
data_dict["table_flow_statistics"] = table_flow_statistics
except requests.exceptions.HTTPError as err:
print "Can not retrieve flow table statistics:", err
# Aggregate flow statistics per host (eg. opendaylight, compute, control and neutron)
try:
aggregate_flow_statistics_url = "%s%s%s%s" % (self._odl_inventory_url,'/node/',self.hosts_dict[host],'/table/0/aggregate-flow-statistics/')
aggregate_flow_statistics = requests.get(aggregate_flow_statistics_url)
aggregate_flow_statistics.raise_for_status()
data_dict["aggregate_flow_statistics"] = aggregate_flow_statistics
except requests.exceptions.HTTPError as err:
pass
#print "Can not retrieve aggregate flow statistics:", err
# Individual flow statistics per host (eg. opendaylight, compute, control and neutron)
data_dict["flow_statistics_list"] = flow_statistics_list
# Port statistics per host (eg. opendaylight, compute, control and neutron)
data_dict["node_connector_list"] = node_connector_list
return data_dict
except ConnectionError:
print("Error fetching data from OpenDaylight.")
def main():
j = requests.get("https://www.citibikenyc.com/stations/json")
for m in j.json()["stationBeanList"]:
conn.setnx(m["stationName"], 0)
availableBikes = {}
while True:
# get the citibike response from their API
r = requests.get("https://www.citibikenyc.com/stations/json")
for m in r.json()["stationBeanList"]:
# for each station, initialise the store if necessary
if m["stationName"] not in availableBikes:
availableBikes[m["stationName"]] = m["availableBikes"]
continue
delta = m["availableBikes"] - availableBikes[m["stationName"]]
# if the number of bikes have changed, emit a message
if delta != 0:
stdout.flush()
conn.set(m["stationName"], delta)
# update the store with the new number of available bikes for that station
availableBikes[m["stationName"]] = m["availableBikes"]
# set system sleep
time.sleep(1)
def query(query_term, folder_name, path):
BASE_URL = 'https://ajax.googleapis.com/ajax/services/search/images?' + 'v=1.0&q=' + query_term + '&start=%d'
BASE_PATH = os.path.join(path, folder_name.replace(' ', '_'))
if not os.path.exists(BASE_PATH):
os.makedirs(BASE_PATH)
print "made: " + BASE_PATH
start = 0 # start query string parameter for pagination
while start < 40: # query 20 pages
r = requests.get(BASE_URL % start)
for image_info in json.loads(r.text)['responseData']['results']:
url = image_info['unescapedUrl']
try:
image_r = requests.get(url)
except ConnectionError, e:
print 'could not download %s' % url
continue
#remove file-system path characters from name
title = query_term.replace(' ', '_') + '_' + image_info['imageId']
file = open(os.path.join(BASE_PATH, '%s.jpg') % title, 'w')
try:
Image.open(StringIO(image_r.content)).save(file, 'JPEG')
except IOError, e:
# throw away gifs and stuff
print 'couldnt save %s' % url
continue
finally:
def print_physiological_state(bb_thr, rr_thr):
""" Retrive and print activity metrics of the specified node. """
# Format the metric requests
addr = 'http://127.0.0.1:8080'
bb_request = ('/eegnode/metric/'
'{"type":"brainbeat",'
'"channels":["ch0", "ch1"],'
'"time_window":[15]}')
rr_request = ('/ecgnode/metric/'
'{"type":"mean_hr",'
'"channels":["ch0"],'
'"time_window":[15],'
'"arguments":[100]}')
# Perform requests
bb = requests.get(addr + bb_request).json()[0]['return']
rr = requests.get(addr + rr_request).json()[0]['return']
if bb > bb_thr and rr > rr_thr:
mwl_class = '1'
else:
mwl_class = '0'
print('%0.2f\t' % bb + '%0.2f\t' % rr + mwl_class)
def test_short_app_params_4():
requests.get(url + '/__engine/1/functions/hello', headers={
'x-lc-sign': sign_by_master_key
})
env = authorization.current_environ
assert env['_app_params']['key'] is None
assert env['_app_params']['master_key'] == TEST_MASTER_KEY
def get_posts_data(
self, blog, id=None, get_comments=False, *args, **options
):
if self.blog_to_migrate == "just_testing":
with open('test-data-comments.json') as test_json:
return json.load(test_json)
self.url = blog
headers = {
'Content-Type': 'application/json',
'Accept': 'application/json',
}
if self.username and self.password:
auth = b64encode(
str.encode('{}:{}'.format(self.username, self.password)))
headers['Authorization'] = 'Basic {}'.format(auth)
if self.url.startswith('http://'):
base_url = self.url
else:
base_url = ''.join(('http://', self.url))
posts_url = ''.join((base_url, '/wp-json/posts'))
comments_url = ''.join((posts_url, '/%s/comments')) % id
if get_comments is True:
comments_url = ''.join((posts_url, '/%s/comments')) % id
fetched_comments = requests.get(comments_url)
comments_data = fetched_comments.text
comments_data = self.clean_data(comments_data)
return json.loads(comments_data)
else:
fetched_posts = requests.get(posts_url, headers=headers)
data = fetched_posts.text
data = self.clean_data(data)
return json.loads(data)
def start_analyzer():
flag = 1
next_article = last_article
counter = 0
gaplimit = 500
while flag == 1:
gaplimit = 50;
# information_json = urllib.request.urlopen(root + api_get_url + next_article).read()
# print(str(information_json)[1:])
counter = counter + 1
information = requests.get(root + api_get_url + str(gaplimit) + "&gapfrom=" + next_article).json()
#print(information)
try:
while gaplimit>9 and information["query-continue"]["images"]["imcontinue"] != "":
print(information["query-continue"]["images"]["imcontinue"])
gaplimit -= 10
if gaplimit == 0:
gaplimit = 1
information = requests.get(root + api_get_url + str(gaplimit) + "&gapfrom=" + next_article).json()
#print(information)
except:
gaplimit = 500
try:
next_article = information["query-continue"]["allpages"]["gapcontinue"]
except:
flag = 0
write_or = True
for page in information["query"]["pages"]:
if write_or:
print(information["query"]["pages"][page]["fullurl"])
write_or = False
WebSurfer.check_page(information["query"]["pages"][page])
def downloadXkcd(startComic, endComic):
for urlNumber in range(startComic, endComic):
# download the page
print('Downloading page http://xkcd.com/%s...' % (urlNumber))
res = requests.get('http://xkcd.com/%s' % (urlNumber))
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text)
# find the url of the comic image
comicElem = soup.select('#comic img')
if comicElem == []:
print('Could not find comic image.')
else:
comicUrl = comicElem[0].get('src')
# download the image
print('Downloading image %s...' % (comicUrl))
res = requests.get(comicUrl)
res.raise_for_status()
# sav img to ./xkcd
imageFile = open(os.path.join('xkcd', os.path.basename(comicUrl)), 'wb')
for chunk in res.iter_content(1000000):
imageFile.write(chunk)
imageFile.close()
def login_success(token, profile):
if profile['email'] in allowed_users:
return render_template('home.html')
#return jsonify(token=token, profile=profile)
else:
requests.get('https://accounts.google.com/o/oauth2/revoke?token='+token['access_token'])
return """
def run():
responses.add(
responses.GET, 'http://example.com/?test=1',
match_querystring=True)
with pytest.raises(ConnectionError):
requests.get('http://example.com/foo/?test=2')
def main():
soup = BeautifulSoup(requests.get('https://news.ycombinator.com/news').content)
links=soup.find_all('span', attrs={'class':'deadmark'})
for link in links:
webpage = link.next_sibling.get('href')
content = BeautifulSoup(requests.get(webpage).content).body.get_text()
printf((webpage, hls().get(content)))
def deploy_test_app_and_check(self, app, test_uuid):
"""This method deploys the test server app and then
pings its /operating_environment endpoint to retrieve the container
user running the task.
In a mesos container, this will be the marathon user
In a docker container this user comes from the USER setting
from the app's Dockerfile, which, for the test application
is the default, root
"""
if 'container' in app and app['container']['type'] == 'DOCKER':
marathon_user = '******'
else:
marathon_user = app.get('user', self.default_os_user)
with self.deploy_and_cleanup(app) as service_points:
r = requests.get('http://{}:{}/test_uuid'.format(service_points[0].host, service_points[0].port))
if r.status_code != 200:
msg = "Test server replied with non-200 reply: '{0} {1}. "
msg += "Detailed explanation of the problem: {2}"
raise Exception(msg.format(r.status_code, r.reason, r.text))
r_data = r.json()
assert r_data['test_uuid'] == test_uuid
r = requests.get('http://{}:{}/operating_environment'.format(
service_points[0].host,
service_points[0].port))
if r.status_code != 200:
msg = "Test server replied with non-200 reply: '{0} {1}. "
msg += "Detailed explanation of the problem: {2}"
raise Exception(msg.format(r.status_code, r.reason, r.text))
assert r.json() == {'username': marathon_user}
def do_api_request(api_link, method='GET', params={}):
# add sendgrid user & api key
params.update({
'api_user': settings.get('sendgrid_user'),
'api_key': settings.get('sendgrid_secret')
})
try:
if method.upper() == 'GET':
if len(params.keys()) > 0:
r = requests.get(
api_link,
params=params,
verify=False
)
else:
r = requests.get(
api_link,
verify=False
)
else:
r = requests.post(
api_link,
params=params,
verify=False
)
response = r.json()
except:
response = {}
if settings.get('environment') == "dev":
logging.info("=================")
logging.info( api_link)
logging.info( json.dumps(params, indent=4))
logging.info( response)
logging.info( "=================")
return response
def get_all_messages(self):
print "Reading messages..."
r = requests.get("https://api.groupme.com/v3/groups/"
+ self.gid + "/messages",
params = {"token": self.key, "limit": 100})
message_count = r.json()["response"]["count"]
i = 0
out = []
while r.status_code is 200 and i < message_count:
progress(i, message_count)
resp = r.json()["response"]
messages = resp["messages"]
for message in messages:
if message["system"] or message["text"] is None:
continue
if message["sender_type"] == u'bot':
continue
# ignore bot commands
if message["text"].startswith("/bot"):
continue
out += [message]
i += len(messages)
last_id = messages[-1]["id"]
r = requests.get("https://api.groupme.com/v3/groups/"
+ self.gid + "/messages",
params = {"token": self.key, "limit": 100, "before_id": last_id})
return out
def search():
query = raw_input('Search: ').replace (" ", "+")
url = base_url_search+snip+"&q="+query+"&type=video"+key
content = json.loads(requests.get(url).text)
stuff=[]
stuff = gets_video_id(content)
num=0
channelTitle = content['items'][0]['snippet']['channelTitle'].capitalize()
num_results=float(int(content['pageInfo']['totalResults']))
while content['nextPageToken'] and num<5:
next_page=content['nextPageToken'].encode('UTF8')
content=''
url = base_url_search+snip+"&q="+query+"&type=video&pageToken="+next_page+key
content = json.loads(requests.get(url).text)
num+=1
for videos in content['items']:
if videos['id']['kind']=='youtube#video':
vid_ids=videos['id']['videoId']
stuff.append(vid_ids)
stuff = [x.encode('UTF8') for x in stuff]
chunks=[stuff[i:i+50] for i in range(0, len(stuff), 50)]
return chunks, stuff, channelTitle, num_results
def test_max_timeout(self):
with SplashServer(extra_args=['--max-timeout=0.1']) as splash:
r1 = requests.get(
url=splash.url("render.html"),
params={
'url': self.mockurl("delay?n=1"),
'timeout': '0.2',
},
)
self.assertStatusCode(r1, 400)
r2 = requests.get(
url=splash.url("render.html"),
params={
'url': self.mockurl("delay?n=1"),
'timeout': '0.1',
},
)
self.assertStatusCode(r2, 504)
r3 = requests.get(
url=splash.url("render.html"),
params={
'url': self.mockurl("delay?n=1")
},
)
self.assertStatusCode(r3, 504)
r4 = requests.get(
url=splash.url("render.html"),
params={
'url': self.mockurl("")
},
)
self.assertStatusCode(r4, 200)
def set_html(self):
r = requests.get(self.url)
# Handle deleted checklists
if r.status_code == 400:
return None
return BeautifulSoup(r.text, features="html.parser")
def fetch_max_item_id(self) -> int:
return requests.get(f"{HN_BASE_URL}/maxitem.json", timeout=5).json()
def get_group(self, group_id):
try:
response = requests.get(self.base_url + '/groups/' + str(group_id) + self.notification_url, auth=self.voiceit_basic_auth_credentials, headers=self.headers)
return response.json()
except requests.exceptions.HTTPError as e:
return e.read()
def get_resource(resource_id):
apitext = SERVER + "/resources/" + resource_id + TOKEN
response = requests.get(apitext)
return response
def index():
if request.method == 'POST':
searchString = request.form['content'].replace(
" ", "") # obtaining the search string entered in the form
try:
dbConn = pymongo.MongoClient(
"mongodb://localhost:27017/") # opening a connection to Mongo
db = dbConn[
'crawlerDB'] # connecting to the database called crawlerDB
reviews = db[searchString].find(
{}
) # searching the collection with the name same as the keyword
if reviews.count(
) > 0: # if there is a collection with searched keyword and it has records in it
return render_template(
'results.html',
reviews=reviews) # show the results to user
else:
flipkart_url = "https://www.flipkart.com/search?q=" + searchString # preparing the URL to search the product on flipkart
uClient = uReq(
flipkart_url) # requesting the webpage from the internet
flipkartPage = uClient.read() # reading the webpage
uClient.close() # closing the connection to the web server
flipkart_html = bs(
flipkartPage, "html.parser") # parsing the webpage as HTML
bigboxes = flipkart_html.findAll(
"div", {"class": "bhgxx2 col-12-12"}
) # seacrhing for appropriate tag to redirect to the product link
del bigboxes[
0:
3] # the first 3 members of the list do not contain relevant information, hence deleting them.
box = bigboxes[0] # taking the first iteration (for demo)
productLink = "https://www.flipkart.com" + box.div.div.div.a[
'href'] # extracting the actual product link
prodRes = requests.get(
productLink) # getting the product page from server
prod_html = bs(
prodRes.text,
"html.parser") # parsing the product page as HTML
commentboxes = prod_html.find_all('div', {
'class': "_3nrCtb"
}) # finding the HTML section containing the customer comments
table = db[
searchString] # creating a collection with the same name as search string. Tables and Collections are analogous.
#filename = searchString+".csv" # filename to save the details
#fw = open(filename, "w") # creating a local file to save the details
#headers = "Product, Customer Name, Rating, Heading, Comment \n" # providing the heading of the columns
#fw.write(headers) # writing first the headers to file
reviews = [] # initializing an empty list for reviews
# iterating over the comment section to get the details of customer and their comments
for commentbox in commentboxes:
try:
name = commentbox.div.div.find_all(
'p', {'class': '_3LYOAd _3sxSiS'})[0].text
except:
name = 'No Name'
try:
rating = commentbox.div.div.div.div.text
except:
rating = 'No Rating'
try:
commentHead = commentbox.div.div.div.p.text
except:
commentHead = 'No Comment Heading'
try:
comtag = commentbox.div.div.find_all(
'div', {'class': ''})
custComment = comtag[0].div.text
except:
custComment = 'No Customer Comment'
#fw.write(searchString+","+name.replace(",", ":")+","+rating + "," + commentHead.replace(",", ":") + "," + custComment.replace(",", ":") + "\n")
mydict = {
"Product": searchString,
"Name": name,
"Rating": rating,
"CommentHead": commentHead,
"Comment": custComment
} # saving that detail to a dictionary
x = table.insert_one(
mydict
) #insertig the dictionary containing the rview comments to the collection
reviews.append(
mydict) # appending the comments to the review list
return render_template(
'results.html',
reviews=reviews) # showing the review to the user
except:
return 'something is wrong'
#return render_template('results.html')
else:
return render_template('index.html')
def feach(url):
r = requests.get(url)
return r.text.replace('\t','')
def pastebin_search(args, lookup, reportDir, apiKeyDir):
userAgent = {'User-agent': 'Mozilla/5.0'}
#return values
pasteScrapeUrl = []
pasteScrapeContent = []
pasteScrapeResult = []
# check for empty args
if args.pastebinsearch is not None:
for a in args.pastebinsearch:
#init lists
scrapeURL = []
scrapeContent = []
#iterate the lookup list
for i, l in enumerate(lookup):
#init textfiles
scrapedFile = open(
reportDir + l + '/' + l + '_pastebin_content.txt', 'w')
pasteUrlFile = open(
reportDir + l + '/' + l + '_pastebin_urls.txt', 'w')
#show user whiat is being searched
print '[+] Searching Pastebin for public pastes containing %s' % (
l)
print '[i] May require a Pastebin Pro account for IP whitelisting'
#run google query code
try:
#iterate url results from search of dork arg and supplied lookup value against pastebin. return top 20 hits
for url in search(str(a) + ' ' + str(l) +
' site:pastebin.com',
stop=20):
#delay 1 second to be polite
time.sleep(1)
#append results together
scrapeURL.append(url)
if args.verbose is True:
print '[+] Paste containing "%s" and "%s" found at: %s' (
a, l, url)
except Exception:
print '[-] Error dorking pastebin URLs, skipping...'
pasteScrapeResult.append('Error scraping Pastebin')
continue
for u in scrapeURL:
#http://docs.python-guide.org/en/latest/scenarios/scrape/
try:
page = requests.get(u, headers=userAgent)
pasteUrlFile.writelines(u)
except:
print '[-] Error opening ' + u + ':'
pasteScrapeResult.append('Error opening %s' % u)
continue
#build html tree
tree = html.fromstring(page.content)
#if verbose spit out url, search term and domain searched
if args.verbose is True:
print '[+] Looking for instances of %s and %s in %s \n' % (
a, l, url)
#grab raw paste data from the textarea
rawPasteData = tree.xpath(
'//textarea[@class="paste_code"]/text()')
#search lines for lookup and keyword
for line in rawPasteData:
#regex for the lookup value (domain) in that line
#if re.search((str(l)), line):
if str(l) in line:
#if the argument search term is in the line
if a in line:
scrapedFile.writelines(a)
return pasteScrapeResult
def scrape_sites(args, lookup, reportDir, apiKeyDir):
scrapeResult = []
userAgent = {'User-agent': 'Mozilla/5.0'}
a = ''
indeedResult = []
githubResult = []
virusTotalResult = []
vtApiKey = ''
vtParams = {}
if args.scraper is True:
for i, l in enumerate(lookup):
scrapeFile = open(reportDir + l + '/' + l + '_scrape.txt', 'w')
print '[+] Scraping sites using ' + l
#http://www.indeed.com/jobs?as_and=ibm.com&as_phr=&as_any=&as_not=&as_ttl=&as_cmp=&jt=all&st=&salary=&radius=25&fromage=any&limit=500&sort=date&psf=advsrch
#init list and insert domain with tld stripped
#insert lookup value into static urls
scrapeUrls = {\
'indeed':'http://www.indeed.com/jobs?as_and=%s&limit=500&sort=date' % (l.split('.')[0]),\
'github':'https://api.github.com/search/repositories?q=%s&sort=stars&order=desc' % (l.split('.')[0]),#pull off the tld\
#'glassdoor':'https://www.glassdoor.com/Reviews/company-reviews.htm?suggestCount=0&suggestChosen=false&clickSource=searchBtn&typedKeyword=%s&sc.keyword=%s&locT=&locId=' % (l.split('.')[0],l.split('.')[0]),\
#'slideshare':'http://www.slideshare.net/%s' % (l.split('.')[0]),\
'virustotal':'https://www.virustotal.com/vtapi/v2/domain/report',\
'censys':'https://www.censys.io/api/v1'\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
#'':''\
}
for name, url in scrapeUrls.items():
#indeed matches jobs. yeah yeah it doesnt use their api yet
if name == 'indeed':
if args.verbose is True:
print '[+] Searching job postings on indeed.com for %s:' % l.split(
'.')[0]
#http://docs.python-guide.org/en/latest/scenarios/scrape/
try:
ipage = requests.get(url, headers=userAgent)
except:
print '[-] Scraping error on ' + url + ':'
continue
#build html tree
itree = html.fromstring(ipage.content)
#count jobs
jobCount = itree.xpath('//div[@id="searchCount"]/text()')
print '[+] ' + str(
''.join(jobCount)
) + ' Jobs posted on indeed.com that match %s:' % (
l.split('.')[0])
jobTitle = itree.xpath(
'//a[@data-tn-element="jobTitle"]/text()')
indeedResult.append(
'\n[+] Job postings on indeed.com that match %s \n\n' %
l.split('.')[0])
for t in jobTitle:
indeedResult.append(t + '\n')
#github matches search for user supplied domain
#https://developer.github.com/v3/search/
#http://docs.python-guide.org/en/latest/scenarios/json/
if name == 'github':
if args.verbose is True:
print '[+] Searching repository names on Github for %s' % (
l.split('.')[0])
#http://docs.python-guide.org/en/latest/scenarios/scrape/
try:
gpage = requests.get(url, headers=userAgent)
except:
print '[-] Scraping error on ' + url + ':'
continue
#read json response
gitJson = gpage.json()
#grab repo name from json items>index val>full_name
githubResult.append('[+] Github repositories matching ' +
(l.split('.')[0]) + '\n\n')
for i, r in enumerate(gitJson['items']):
githubResult.append(gitJson['items'][i]['full_name'] +
'\n')
if name == 'virustotal':
if not os.path.exists(apiKeyDir + 'virus_total.key'):
print '[-] You are missing %s/virus_total.key' % apiKeyDir
#vtApiKey=raw_input("Please provide an API Key: ")
#read API key
try:
with open(apiKeyDir + 'virus_total.key',
'r') as apiKeyFile:
for k in apiKeyFile:
vtApiKey = k
except:
print '[-] Error opening %s/virus_total.key key file, skipping. ' % apiKeyDir
continue
if args.verbose is True:
print '[+] VirusTotal domain report for %s' % l
virusTotalResult.append(
'[+] VirusTotal domain report for %s' % l)
vtParams['domain'] = l
vtParams['apikey'] = vtApiKey
#per their api reference
response = urllib.urlopen(
'%s?%s' % (url, urllib.urlencode(vtParams))).read()
#read json response
vtJson = json.loads(response)
#virusTotalResult.append(vtJson)
#write the file
for g in githubResult:
scrapeFile.writelines(''.join(str(g.encode('utf-8'))))
for i in indeedResult:
scrapeFile.writelines(''.join(str(i.encode('utf-8'))))
scrapeResult.append(indeedResult)
scrapeResult.append(githubResult)
#verbosity logic
if args.verbose is True:
for gr in githubResult:
print ''.join(gr.strip('\n'))
for ir in indeedResult:
print ''.join(ir.strip('\n'))
return scrapeResult
import requests,random,sys,time,os,base64,readline,curses
from thread import *
os.system("clear")
heder = requests.get("https://raw.githubusercontent.com/tampansky/visitor/master/user-age.txt").text
heder = heder.split("\n")
#FONT COLOR
h = '\033[92m' # hijau
p = '\033[97m' # putih
m = '\033[91m' # merah
br = '\033[94m' # biru
y = '\033[1;33m' # kuning
blck = "\033[0;30m" #hitam
bu = "\033[0;33m" #abu Abu
pur = "\033[0;35m" # purpel
cy = "\033[0;36m" # cyan
# FONT TYPE
faint = "\033[2m" # faint
bol = "\033[1m" # bold
ita = "\033[3m" # italic
nega = "\033[7m" # negativ
under = "\033[4m" # underline
blink = "\033[5m" # blink
end = "\033[0m" # end
cros = "\033[9m" #crossed
print("tunggu sebentar")
time.sleep(1)
os.system("clear")
print("loading.")
time.sleep(1)
os.system("clear")
print("loading..")
def fetch_item_by_id(self, item_id: int) -> Optional[HNItemRecord]:
item_url = f"{HN_BASE_URL}/item/{item_id}.json"
item = requests.get(item_url, timeout=5).json()
return item
def requete(url):
try:
r = requests.get(url)
return url, r.status_code
except:
pass
def jsonToData(url):
#Calling API
response = requests.get(url)
classicBox = json.loads(response.text)
#JSON to pandas dataframe
return pd.json_normalize(classicBox['items'],record_path=['courses'])
def get_html(url):
html_pack = requests.get(url)
return html_pack.text
reqheaders = {
'X-SOCIALEDGE-ID': '3da9ff7e400b1d535b0115ca064dee02',
'Content-Type': "application/json"
}
Path("./datas/list").mkdir(parents=True, exist_ok=True)
with open("./listIds") as fp:
line = fp.readline()
while line:
id = line.strip()
print(id)
with open("./datas/list/{}.json".format(id), "w") as wfp:
skip = 0
count = 0
while True:
r = requests.get(
"https://api.creatoriq.com/api/view?params[ListId]={}&output=cs&view=List/List&skip={}&take=2000"
.format(id, skip),
headers=reqheaders)
if r.status_code != 200:
raise Exception("error")
data = json.loads(r.text)
if len(data["results"]) == 0:
break
for record in data["results"]:
wfp.write(json.dumps(record) + "\n")
skip += 2000
line = fp.readline()
def get_token(self):
r=requests.get('https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid='
'ww65766ff6db64205d&corpsecret=nC_218vYvuzeQQ_DlrJ-_zik9NQI_FVJblR4k8RW-Lo')
token=r.json()['access_token']
return token
import requests
from pprint import pprint
# json -> dictionary
url = 'https://api.bithumb.com/public/ticker/btc'
data = requests.get(url).json()['data']
pprint(data)
# json은 문자열이므로 형변환
fluctuation = int(data['max_price']) - int(data['min_price'])
if int(data['opening_price']) + fluctuation >= int(data['max_price']):
print('상승장')
else:
print('하락장')
def index():
response = requests.get("http://127.0.0.1:5000/api/provincias")
return render_template('provincias.html', data=response.json())
accept_language = config.get('header', 'Accept-Language')
content_type = config.get('header', 'Content-Type')
auth = config.get('header', 'Authorization')
USER_URL = host + ":" + port + "/" + user_api
kylin_headers = {
'Accept': str(accept),
'Accept-Language': str(accept_language),
'Authorization': str(auth),
'Content-Type': str(content_type)
}
print "Sending URL ==> " + USER_URL + "\n"
response = requests.get(USER_URL, headers=kylin_headers)
print "Response received, validating response \n"
if response.status_code != 200:
print('Error : ' + str(response.status_code))
exit()
else:
print('Status Code : ' + str(response.status_code) + ' Status : SUCCESS')
print "Response : \n"
print(response.json())
print " \n"
print "code : " + response.json()['code'] + "\n"
print "msg : " + response.json()['msg'] + "\n"
def simulate(l, b, beamwidth=0.6, v_min=-400, v_max=400, plot_file=''):
'''
Simulate 21 cm profiles based on the LAB HI Survey.
Args:
l: float. Target galactic longitude [deg]
b: float. Target galactic latitude [deg]
beamwidth: float. Telescope half-power beamwidth (approx. equal to 0.7 * lambda/D) [deg]
v_min: float. Minimum radial velocity (xlim) [km/s]
v_max: float. Maximum radial velocity (xlim) [km/s]
plot_file: string. Output plot filename
'''
import requests
import matplotlib
import matplotlib.pyplot as plt
if plot_file != '':
plt.rcParams['figure.figsize'] = (9,7)
plt.rcParams['legend.fontsize'] = 14
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['axes.titlesize'] = 16
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
# Establish velocity limits
if v_min < -400:
v_min = -400
if v_max > 400:
v_max = 400
# Download LAB Survey HI data
try:
response = requests.get('https://www.astro.uni-bonn.de/hisurvey/euhou/LABprofile/download.php?ral='+str(l)+'&decb='+str(b)+'&csys=0&beam='+str(beamwidth))
except requests.exceptions.ConnectionError:
raise requests.exceptions.ConnectionError('Failed to reach astro.uni-bonn.de. Make sure you are connected to the internet and try again.')
data = response.content
# Parse data
data = data.splitlines()
data = data[4:]
#data = [' '.join(line.split()).replace('\n', '') for line in data]
frequency = []
spectrum = []
for line in data:
try:
frequency.append(float(line.split()[2]))
spectrum.append(float(line.split()[1]))
except IndexError:
break
# Convert km/s to m/s
v_min = v_min*1000
v_max = v_max*1000
# Define Frequency limits
left_frequency_edge = 1420.4057517667 + 1420.4057517667e6 * -v_max/(299792458 * 1e6)
right_frequency_edge = 1420.4057517667 + 1420.4057517667e6 * -v_min/(299792458 * 1e6)
# Limit galactic coordinates to 2 decimal places
l = float('%.2f' % l)
b = float('%.2f' % b)
# Initiate plot
fig, ax = plt.subplots()
try:
plt.title('Simulated HI Profile $(l$=$'+str(l)+'\degree$, $b$=$'+str(b)+'\degree)$ | Beamwidth: $'+str(beamwidth)+'\degree$', pad=40)
except: # Catch missing TeX exception
plt.title('Simulated HI Profile (l='+str(l)+' deg, b='+str(b)+' deg) | Beamwidth: '+str(beamwidth)+' deg', pad=40)
# Plot data
ax.plot(frequency, spectrum, label='LAB Survey')
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel('Brightness Temperature (K)')
ax.set_xlim(left_frequency_edge, right_frequency_edge)
ax.ticklabel_format(useOffset=False)
ax.legend(loc='upper left')
# Set secondary axis for Radial Velocity
ax_secondary = ax.twiny()
ax_secondary.set_xlabel('Radial Velocity (km/s)', labelpad=5)
ax_secondary.axvline(x=0, color='brown', linestyle='--', linewidth=2, zorder=0)
ax_secondary.set_xlim(v_max/1000, v_min/1000)
ax_secondary.tick_params(axis='x', direction='in', pad=2)
ax.grid()
if plot_file != '':
# Save plot to file
plt.savefig(plot_file, bbox_inches='tight', pad_inches=0.1)
else:
# Display plot
plt.show()
plt.clf()
plt.close()
def download_volume(manga_to_download, volume, path_to_download_to, loading_bar, app_root, label, button, button_vol):
if path_to_download_to == "":
print("No argument was given for path_to_download_to")
return
dirpath = tempfile.mkdtemp()
print(dirpath)
button.config(state="disabled")
button_vol.config(state="disabled")
# If there is no connection, display an error
try:
merger = PdfFileMerger()
chapter_list = get_volume_list(manga_to_download, True)[int(volume) - 1]
for i in range(len(chapter_list)):
r = requests.get("https://guya.moe/api/download_chapter/" + manga_to_download + "/" + chapter_list[i].replace(".", "-") + "/", stream=True)
file_size = r.headers.get("content-length")
with open(dirpath + "/chapter.zip", "wb") as file:
if file_size is None:
print("No file size header found, cannot display progress")
file.write(r.content)
else:
downloaded_data = 0
file_size = int(file_size)
for data in r.iter_content(chunk_size=32768):
downloaded_data += len(data)
file.write(data)
progress = int(100 * downloaded_data / file_size)
loading_bar["value"] = progress
label.configure(text=f"{str(progress)}% ({i + 1}/{len(chapter_list)})")
app_root.update_idletasks()
app_root.update()
# Extract the zip file
with zipfile.ZipFile(dirpath + "/chapter.zip", 'r') as zip_ref:
zip_ref.extractall(dirpath)
# Create the PDF file
file_path = dirpath + f"/{chapter_list[i].replace('.', '-')}.pdf"
pdf_maker.make_pdf(dirpath, file_path)
# Append the created file to the volume
print(f"Appended file {file_path}")
merger.append(file_path)
except Exception as e:
mbox.showerror("An error occurred", "Unable to estabilish a connection, check your internet settings")
print("Error: " + str(e))
return
if not path_to_download_to.endswith(".pdf"):
path_to_download_to += ".pdf"
'''
Tried to make this a function in pdf_maker.py, but the pdf was sorted badly
(e. g. chapter 1, then 10-5, then 10 and only then 2) so I decided to append the pdf files right on when they were
created.
'''
merger.write(path_to_download_to)
merger.close()
shutil.rmtree(dirpath)
label.configure(text="Ready")
loading_bar["value"] = 0
button.config(state="normal")
button_vol.config(state="normal")
def get_info():
html = requests.get(url).text
json_dict = json.loads(html)
return json_dict
# ch21_27.py
import bs4, requests, re
url = 'http://www.taiwanlottery.com.tw'
html = requests.get(url)
print("網頁下載中 ...")
html.raise_for_status() # 驗證網頁是否下載成功
print("網頁下載完成")
objSoup = bs4.BeautifulSoup(html.text, 'lxml') # 建立BeautifulSoup物件
dataTag = objSoup.select('.contents_box02') # 尋找class是contents_box02
print("串列長度", len(dataTag))
for i in range(len(dataTag)): # 列出含contents_box02的串列
print(dataTag[i])
pattern=r'\d+/\d+/\d+'
# 找尋開出順序與大小順序的球
balls = dataTag[0].find_all('div', {'class':'ball_tx ball_green'})
date = dataTag[0].find('span', {'class':'font_black15'})
datelist=re.findall(pattern,str(date))
print('威力彩開獎 日期: ' + datelist[0])
print("開出順序 : ", end='')
for i in range(6): # 前6球是開出順序
print(balls[i].text, end=' ')
print("\n大小順序 : ", end='')
for i in range(6,len(balls)): # 第7球以後是大小順序
print(balls[i].text, end=' ')
# 找出第二區的紅球
def browse_types():
types = get(pub_url+"/lookup/publicationtypes", verify=verify_cert).json()
return render_template('pubswh/browse_types.html', types=types)
def thumb(char, ts=ts, api_key=api_key, hash_key=hash1):
url = "http://gateway.marvel.com/v1/public/characters?ts={}&apikey={}&hash={}&nameStartsWith={}".format(
ts, api_key, hash_key, char)
response = requests.get(url).json()
image = response['data']['results'][0]['thumbnail']['path'] + "/detail.jpg"
return image
# coding=utf-8
# author=yphacker
import re
import bz2
import requests
url = 'http://www.pythonchallenge.com/pc/def/integrity.html'
content = requests.get(url).content#.decode('utf-8')
un = re.findall(b"un: '([^']+)'", content)[0]
pw = re.findall(b"pw: '([^']+)'", content)[0]
print(un)
print(pw)
print('username:'******'unicode_escape').encode('latin1')))
print('password:'******'unicode_escape').encode('latin1')))
def get_coords():
''' Get coordinates based on the script's IP address '''
response = requests.get("http://ipinfo.io").json()
lat, lon = response["loc"].split(',')
return lat, lon
def get_statuses(self):
response = requests.get(self.get_url('/issue_statuses.json'),
data={'key': self.config['api_key']})
return json.loads(response.text)['issue_statuses']
def main():
day, current_time = get_date_time()
full_url = build_url(day)
try:
response = requests.get(full_url)
if response.status_code == 200:
vendors_data = response.json()
vendors_data.sort(key = lambda x: x["applicant"]) # sort by the 'applicant' field (assuming this is the name of the Food Truck Vendor)
index = 0 # the index of the current Vendor we are looking at
vendors_displayed_so_far = 0
display_more = True
while display_more:
try: # use a try-except statement to avoid checking the length of the entire response
if vendors_displayed_so_far < 10:
if vendors_data[index]["start24"] <= current_time <= vendors_data[index]["end24"]: # if the current time is in between a vendor's opening and closing hours
print("{} {}".format(vendors_data[index]["applicant"], vendors_data[index]["location"]))
vendors_displayed_so_far += 1
index += 1
else:
ask_for_input = True
while ask_for_input:
user_input = input("\nShow more rows? Enter 'Yes' or 'No' ")
if user_input.lower() == "yes":
ask_for_input = False
vendors_displayed_so_far = 0
elif user_input.lower() == "no":
ask_for_input = False
display_more = False
else:
print("\nYou didn't enter 'Yes' or 'No'. Try again!")
except IndexError as e: # there are no more Food Trucks to display
print("\nNo more restauraunts to find. That's it!\n")
break
else:
sys.exit("Server responded with status code {} instead of 200.".format(response.status_code))
# Exception Handling
except requests.exceptions.HTTPError as e:
print("An HTTP Error occurred with the following message: {}".format(e))
sys.exit(1)
except requests.exceptions.ConnectionError as e:
print("A Connection Error occurred with the following message: {}".format(e))
sys.exit(1)
except requests.exceptions.ConnectTimeout as e:
print("A Connect Timeout Error (request timed out while trying to connect to the server) occurred with the following message: {}".format(e))
sys.exit(1)
except requests.exceptions.ReadTimeout as e:
print("A Read Timeout Error (server did not send any data in the allotted amount of time) occurred with the following message: {}".format(e))
sys.exit(1)
except requests.exceptions.URLRequired as e:
print("A URL Required Error (invalid URL) occurred with the following message: {}".format(e))
sys.exit(1)
except requests.RequestException as e:
print("An ambiguous Request Exception Error occurred: {}".format(e))
sys.exit(1)
def cnnTimer():
# while True:
r = requests.get('https://www.googleapis.com/youtube/v3/search?part=snippet&fields=items/snippet/description,items/id/videoId&channelId=' + CNN_CHANNEL_ID + '&maxResults=1&order=date&type=video&key=AIzaSyAjM0NQVnhEvRY15_bhib3y1m0ilQjdjx0')
description = json.loads(r.text)
id = description["items"][0]["id"]["videoId"]
print(id)
def get_task(self, task_id):
response = requests.get(self.get_url('/issues/{}.json'.format(task_id)),
data={'key': self.config['api_key']})
return json.loads(response.text)['issue']
