def fetch_home(self): extractor = Extractor(self.baseurl, self.settings) channels = extractor.get_channels() self.cache_clear() self.cacheManager.store(channels) return channels
def __init__(self): self.server = pyo.Server(nchnls=1).boot() self.server.setAmp(0.3) self.inp = pyo.Input() self.extractor = Extractor(self.inp) self.chain = Chain(self.inp) self.player = ChainWaver(self.chain, self.extractor).out()
def extract(url): r = requests.get(url) html = r.text extracted = Extractor().extract(html, source_url=url) u = URL(url) qs = u.get_qs extracted.update({'qs': qs.items()}) return extracted
def get_place_context(url=None, text=None): e = Extractor(url=url, text=text) e.find_entities() pc = PlaceContext(e.places) # pc.set_countries() # pc.set_regions() # pc.set_cities() # pc.set_other() return pc
def __init__(self, client=None, host='localhost', port=28015, overwrite=False): "Initialize a Crawler." self._client = client self.host = host self.port = port self.overwrite = overwrite self.extractor = Extractor() self.log = logging.getLogger(self.__class__.__name__)
def handle(self): block = self.cache_load() extractor = Extractor(block['url'], self.settings) videos = extractor.get_live_videos() livefilter = self.settings.livefilter() logger.debug('Filtering live streams for {}.', livefilter) if livefilter != 'all': videos = [ video for video in videos if 'sport' in video and video['sport'] == livefilter ] self.add_all_entries(videos)
def handle(self): if self.url is None: block = self.cache_load() else: logger.debug('Load block from "{}"', self.url) block = {'url': self.url} logger.debug('Block: {}', block) if 'url' in block: extractor = Extractor(block['url'], self.settings) videos = extractor.get_videos() else: videos = block['children'] self.add_all_entries(videos)
def parse(self, content): """Parses html content of http response body into a single :class:`~news.models.abstract.Readable`. Internally uses :class:`~extraction.Extractor` extractor to extract sementic tags from the plain html content. :param content: Http response body :type content: :class:`str` :returns: A parsed readable :rtype: :class:`~news.models.abstract.Readable` """ extractor = Extractor() extracted = extractor.extract(content) return Readable(url=self.url, title=extracted.title, content=content, summary=extracted.description, image=extracted.image)
def handle(self): if len(self.idParts) == 0: channelsOrBlocks = self.fetch_home() else: channel = self.cache_load() if not channel: self.fetch_home() channel = self.cache_load() if 'children' in channel: channelsOrBlocks = channel['children'] else: extractor = Extractor(channel['url'], self.settings) channelsOrBlocks = extractor.get_blocks() self.cache_store(channelsOrBlocks) self.add_all_entries(channelsOrBlocks)
import cv2 import numpy as np from extraction import Extractor from grid import Grid from mod_source import draw_boxes, draw_numbers COLOUR_GREEN = (0, 255, 0) COLOR_RED = (0, 0, 255) X = [] indices = [] grid = Grid() extractor = Extractor() video_capture = cv2.VideoCapture(0) def create_grid(valid_grid, extractor, X, indices): '''Create Sudoku grid from image if possible. ''' images = extractor.valid_extraction(valid_grid) if not images: return False for i in images['NN']: X.append(i[0]) indices.append(i[1]) X = np.array(X) X = X.reshape(X.shape[0], 28, 28, 1) return [X, indices]