Loading tagthunder/pipeline/experimentations/segmentation/data/example.html 0 → 100644 +14 −0 Original line number Diff line number Diff line <html> <body bbox="0 80 1200 252.875" style="display: block; visibility: visible;" xpath="/html/body"> <div bbox="268 80 664 252.875" style="display: block; visibility: visible;" xpath="/html/body/div"><h1 bbox="300 133.4375 600 38" style="display: block; visibility: visible;" xpath="/html/body/div/h1">Example Domain</h1> <p bbox="300 192.875 600 57" style="display: block; visibility: visible;" xpath="/html/body/div/p[1]">This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.</p> <p bbox="300 265.875 600 19" style="display: block; visibility: visible;" xpath="/html/body/div/p[2]"><a bbox="300 265.875 152.359375 19" href="https://www.iana.org/domains/example" style="display: inline; visibility: visible;" xpath="/html/body/div/p[2]/a">More information...</a></p> </div> </body> </html> No newline at end of file tagthunder/pipeline/experimentations/segmentation/tdbu.py +8 −2 Original line number Diff line number Diff line import pprint from pipeline.blocks.cleaning import VisionBased from pipeline.blocks.segmentation import TopDownBottomUp from pipeline.experimentations.segmentation.visualisation import PlotClustering Loading @@ -7,14 +9,18 @@ from pipeline.models.responses import HTMLPP, Segmentation, HTMLP def main(htmlpp: HTMLPP): algo = TopDownBottomUp() segmentation: Segmentation = algo(htmlpp, nb_zones=5) return segmentation def vizu(segmentation): plot = PlotClustering(nrows=2) plot.plot_centers("TDBU", centers=segmentation.htmlpp) plot.show() if __name__ == '__main__': file = "data/calvados.html" file = "data/example.html" with open(file, "r") as f: htmlpp = VisionBased()(HTMLP(f)) main(htmlpp) segmentation = main(htmlpp) pprint.pp(segmentation.zones) tagthunder/pipeline/experimentations/vocalization/google_tts.py +1 −1 Original line number Diff line number Diff line Loading @@ -3,7 +3,7 @@ import io from pydub import AudioSegment from pydub.playback import play from pipeline.blocks.vocalization.google_tts import GoogleTTS from pipeline.blocks.vocalization.utils.text_to_speech import GoogleTTS from pipeline.models.responses import Keyword, Keywords Loading Loading
tagthunder/pipeline/experimentations/segmentation/data/example.html 0 → 100644 +14 −0 Original line number Diff line number Diff line <html> <body bbox="0 80 1200 252.875" style="display: block; visibility: visible;" xpath="/html/body"> <div bbox="268 80 664 252.875" style="display: block; visibility: visible;" xpath="/html/body/div"><h1 bbox="300 133.4375 600 38" style="display: block; visibility: visible;" xpath="/html/body/div/h1">Example Domain</h1> <p bbox="300 192.875 600 57" style="display: block; visibility: visible;" xpath="/html/body/div/p[1]">This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.</p> <p bbox="300 265.875 600 19" style="display: block; visibility: visible;" xpath="/html/body/div/p[2]"><a bbox="300 265.875 152.359375 19" href="https://www.iana.org/domains/example" style="display: inline; visibility: visible;" xpath="/html/body/div/p[2]/a">More information...</a></p> </div> </body> </html> No newline at end of file
tagthunder/pipeline/experimentations/segmentation/tdbu.py +8 −2 Original line number Diff line number Diff line import pprint from pipeline.blocks.cleaning import VisionBased from pipeline.blocks.segmentation import TopDownBottomUp from pipeline.experimentations.segmentation.visualisation import PlotClustering Loading @@ -7,14 +9,18 @@ from pipeline.models.responses import HTMLPP, Segmentation, HTMLP def main(htmlpp: HTMLPP): algo = TopDownBottomUp() segmentation: Segmentation = algo(htmlpp, nb_zones=5) return segmentation def vizu(segmentation): plot = PlotClustering(nrows=2) plot.plot_centers("TDBU", centers=segmentation.htmlpp) plot.show() if __name__ == '__main__': file = "data/calvados.html" file = "data/example.html" with open(file, "r") as f: htmlpp = VisionBased()(HTMLP(f)) main(htmlpp) segmentation = main(htmlpp) pprint.pp(segmentation.zones)
tagthunder/pipeline/experimentations/vocalization/google_tts.py +1 −1 Original line number Diff line number Diff line Loading @@ -3,7 +3,7 @@ import io from pydub import AudioSegment from pydub.playback import play from pipeline.blocks.vocalization.google_tts import GoogleTTS from pipeline.blocks.vocalization.utils.text_to_speech import GoogleTTS from pipeline.models.responses import Keyword, Keywords Loading