diff options
| author | Guillaume Horel <guillaume.horel@serenitascapital.com> | 2014-02-27 13:56:11 -0500 |
|---|---|---|
| committer | Guillaume Horel <guillaume.horel@serenitascapital.com> | 2014-02-27 13:56:11 -0500 |
| commit | f96752448a537bd6a3378a83ab0e8476653ec59c (patch) | |
| tree | 14669d6d10e9d0343a33b32bf2ab7197fd25b84a /parsedjvutext.py | |
| parent | 0d583ea5f9873a5b2a22a89bbb979bf08dd05a90 (diff) | |
| download | ocr-layer-curation-f96752448a537bd6a3378a83ab0e8476653ec59c.tar.gz | |
cleanup
Diffstat (limited to 'parsedjvutext.py')
| -rw-r--r-- | parsedjvutext.py | 28 |
1 files changed, 0 insertions, 28 deletions
diff --git a/parsedjvutext.py b/parsedjvutext.py index 9855786..a13421a 100644 --- a/parsedjvutext.py +++ b/parsedjvutext.py @@ -6,34 +6,6 @@ from djvu.decode import Context from itertools import chain import collections - -def parse_book_xml(djvubook): - args = ["djvutoxml", djvubook] - soup = BeautifulSoup(subprocess.check_output(args), "lxml") - words = [] - coords = [] - for page in soup.find_all("hiddentext"): - words.append([word.text for word in page.find_all("word")]) - coords.append([tuple(map(int, word["coords"].split(","))) - for word in page.find_all("word")]) - return {"words": words, "coords": coords} - - -def get_npages(djvubook): - args = ["djvused", "-e", "n", djvubook] - return int(subprocess.check_output(args)) - - -def parse_page_xml(djvubook, pagenumber): - args = ["djvutoxml", "--page", str(pagenumber), djvubook] - soup = BeautifulSoup(subprocess.check_output(args), "lxml") - all_words = soup.find_all("word") - words = [word.text for word in all_words] - coords = [tuple(map(int, word["coords"].split(","))) - for word in all_words] - return {"words": words, "coords": coords} - - def parse_page(page, html=False): s, page_size = page.text.sexpr, page.size[1] |
