def test_iter_pages(self):
pdf_file = os.path.join(RESOURCE_ROOT, 'CSE_Result.pdf')
for i, page in enumerate(
ggsipu_result.iter_pages(pdf_file, verbose=True)):
with open(
os.path.join(RESOURCE_ROOT, 'CSE_Result',
str(i + 1) + '.txt'), 'r') as txtf:
self.assertEqual(txtf.read(), page)
def get_2018_result(pdf):
results = {}
for page in iter_pages(pdf):
if has_page_results(page):
results.update(
{r.roll_num: r
for r in iter_results(page) if r.batch == 2018})
return results
from ggsipu_result import iter_pages, iter_results, has_page_results
FILE = "document1.pdf"
cgpa = []
for page in iter_pages(FILE):
if has_page_results(page):
for res in iter_results(page):
# Filtered for specific batch
if res.batch == 2018:
cgpa.append(res.cgpa)
avg_cgpa = sum(i for i in cgpa) / len(cgpa)
print(avg_cgpa)
import ggsipu_result
FILE = "document1.pdf"
with open('subj_dump.json', 'a') as fs, open('res_dump.json', 'a') as fr:
for page in ggsipu_result.iter_pages(FILE):
if ggsipu_result.has_page_results(page):
results = list(ggsipu_result.iter_results(page))
fr.write(ggsipu_result.toJSON(results))
elif ggsipu_result.has_page_subejcts(page):
subjects = list(ggsipu_result.iter_subjects(page))
fs.write(ggsipu_result.toJSON(subjects))
from ggsipu_result import iter_pages
FILE = 'document1.pdf'
for i, page in enumerate(iter_pages(FILE)):
with open(str(i + 1) + ".txt") as f:
f.write(page)