def devide_jpgs(jpg_dir, norm_img_size=True):
'''カラーならc.jpg、グレーでよければグレスケ化してg.jpgで保存'''
out_dir = utils.make_outdir(jpg_dir, NEW_JPG_DIR)
for jpg_path in utils.get_path_list(jpg_dir, 'jpg'):
img = cv2.imread(jpg_path)
if img is None:
continue
# norm_img_sizeが指定されていればリサイズ
if norm_img_size:
img = utils.img_resize(img, max_height=config.MAX_HEIGHT)
if is_color_img(img):
cv2.imwrite(
join(out_dir,
basename(jpg_path).replace('.jpg', 'c.jpg')), img)
else:
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv2.imwrite(
join(out_dir,
basename(jpg_path).replace('.jpg', 'g.jpg')), img)
if args.with_subtitle or args.shave_subtitle:
good_cons_num_y += 1
# 出力ディレクトリ・パスを準備
outdir_name = '2_paint_out'
output_path = utils.make_outdir(image_dir, outdir_name)
output_koma_path = utils.make_outdir(output_path, '0_koma')
if len(os.listdir(output_koma_path)) >= 3:
shutil.rmtree(output_path)
output_path = utils.make_outdir(image_dir, outdir_name)
output_koma_path = utils.make_outdir(output_path, '0_koma')
output_shaved_path = utils.make_outdir(output_koma_path, '0_padding_shave')
# paint_out処理: 1st
img_path_list = utils.get_path_list(image_dir, args.ext)
print('pages:', len(img_path_list) - (args.start + args.end))
with utils.timer('paint_out処理: 1st 切り抜き位置が求められた画像を切り抜き'):
odd_cp_list = [] # 奇数idxページのカットポイントを格納
even_cp_list = [] # 偶数idxページのカットポイントを格納
not_cut_img_path_dict = {}
exec_paint_out_cut(img_path_list, kind='1st')
# 平均切り出し座標を算出
even_page_cp = find_average_point(even_cp_list)
odd_page_cp = find_average_point(odd_cp_list)
print('lens', len(img_path_list) - len(not_cut_img_path_dict))
# 平均切り出し座標から画像を切り出すループ
if not_cut_img_path_dict:
# 1ページの画像から各コマを切り出す処理
import os
import sys
import cv2
from cut import AverageDiffCut
import utils
if __name__ == '__main__':
image_dir = utils.check_argv_path(sys.argv)
outdir_name = 'koma'
output_path = utils.make_outdir(image_dir, outdir_name)
img_path_list = utils.get_path_list(image_dir, 'jpg')
adc = AverageDiffCut()
# 切り出し座標＝カットポイント(cp)を探すためのループ
print('切り出し座標を検出しています')
odd_cp_list = [] # 奇数idxページのカットポイントを格納
even_cp_list = [] # 偶数idxページのカットポイントを格納
not_cut_img_path_dict = {}
for idx, img_path in enumerate(img_path_list):
img = cv2.imread(img_path)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 切り出し座標の探索
cp_dict = adc.search_cut_point(img_gray)
print(idx, cp_dict, len(cp_dict['x']), len(cp_dict['y']))
# 切り出し座標が規定の数だけ帰ってきたらリストに追加
# エラーが出たら( ˘ω˘)ｽﾔｧ
print(e)
req_count += 1
if req_count < 5:
# sleep_timeが徐々に伸びるように設定
sleep_time = 2 ** req_count
print('retry after {} second'.format(sleep_time))
sleep(sleep_time)
else:
# 呼び出し元でエラー内容等を表示
raise
return
if __name__ == '__main__':
pdf_dir = utils.check_argv_path(sys.argv)
pdf_path_list = utils.get_path_list(pdf_dir, 'pdf')
# 処理済みのファイルを雑に判別して除外
# pdf_path_list = [p for p in pdf_path_list if not os.path.basename(p).startswith('[')]
amazon_url_list = []
for pdf_path in pdf_path_list:
isbn = pdf_to_isbn(pdf_path)
if isbn:
try:
amazon_items = fetch_amazon_item(isbn)
except HTTPError as e:
print('情報の取得に失敗しました:', pdf_path, isbn)
continue
if amazon_items:
amazon_url = get_amazon_url(amazon_items)
print(amazon_url)
amazon_url_list.append(amazon_url)
def pdf_to_page1(pdf_path):
with open(pdf_path, 'rb') as fp:
parser, document = prev_pdf_parser(fp)
# Check if the document allows text extraction. If not, abort.
if not document.is_extractable:
raise PDFException
# 最初のページを取得
page1 = PDFPage.create_pages(document).__next__()
layouts = prev_pdf_layout(page1)
for layout in layouts:
for thing in layout:
save_image(thing,
dirname(pdf_path),
TMP_FILENAME_PAGE1,
max_width=MAX_WIDTH_JPG1)
return join(dirname(pdf_path), TMP_FILENAME_PAGE1)
if __name__ == '__main__':
pdf_dir = utils.check_argv_path(sys.argv)
pdf_path_list = utils.get_path_list(pdf_dir, 'pdf')
pdf_path_list = [path for path in pdf_path_list if not os.path.isdir(path)]
pdf_to_jpg_dir = utils.make_outdir(pdf_dir, PDF_TO_JPG_DIR)
print('pdf files:', len(pdf_path_list))
for pdf_path in pdf_path_list:
pdf_to_jpg(pdf_path)
for v in text['boundingPoly']['vertices']]
draw.line(box + [box[0]], width=2, fill=color)
return img
if __name__ == '__main__':
image_dir = Path(utils.check_argv_path(sys.argv))
key_file_path = '/Users/esuji/Dropbox/program/cvtest/yonkoma2data/src/MyFirstProject-b8427fd28b8d.json'
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = key_file_path
# Instantiates a client
client = vision.ImageAnnotatorClient()
pickle_dir = utils.make_outdir(image_dir / '..', 'pickles')
image_path_list = sorted(utils.get_path_list(image_dir, '.jpg'))
ta_list = []
for idx_koma, image_path in enumerate(image_path_list[100:110]):
print(idx_koma, image_path)
try:
image = get_image(image_path)
ta = get_response_text_annotations(image)
ta_list.append({
'image_path': image_path,
'text_annotation': list(ta)
})
print(ta[0].description)
except Exception as e:
print(e)