def data_collector(sample_id, sample_type, report_type, doc_type, req):
if doc_type == 'html':
#do stuff
if req == "intro":
return intro(sample_id, sample_type)
if req == "name":
return name_collector(sample_id, sample_type)
if req == "gene":
return feature_gene(sample_id, sample_type)
if req == "stem-loop":
return feature_stem_loop(sample_id, sample_type)
if req == "peptide":
return feature_peptide(sample_id, sample_type)
if req == "cds":
return feature_cds(sample_id, sample_type)
if req == "source":
return feature_source(sample_id, sample_type)
if req == "comment":
return comment(sample_id, sample_type)
if req == "sequence":
return chain_sequence(sample_id, sample_type)
if req == "all":
return soup_collector(sample_id, sample_type).text
else:
print('Invalid parameter supplied!')
else:
url = "https://www.ncbi.nlm.nih.gov/sviewer/viewer.fcgi?id=" + sample_id + "&db=" + sample_type + "&report=" + report_type + "&extrafeat=null&conwithfeat=on&retmode=" + doc_type + "&tool=portal&maxdownloadsize=1000000"
data = requests.get(url)
soup = bs(data.content, 'html.parser')
for script in soup(["script", "style"]):
script.decompose()
return soup, url
def stem(spl_id_dup, spl_type_dup):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
iterator = 0
while True:
stem_loop = soup.find('span', {"id": "feature_" + sample_info_name + "_stem_loop_" + str(iterator)})
if stem_loop == None:
break
print(stem_loop.text)
iterator += 1
def sequence(spl_id_dup, spl_type_dup):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
iterator = 1
while True:
source = soup.find('span',
{"id": sample_info_name + "_" + str(iterator)})
if source == None:
break
iterator += 60
print(iterator, source.text)
def gene(spl_id_dup, spl_type_dup):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
iterator = 0
while True:
gene = soup.find('span', {
"id":
"feature_" + sample_info_name + "_gene_" + str(iterator)
})
if gene == None:
break
print(gene.text)
iterator += 1
def cds(spl_id_dup, spl_type_dup):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
iterator = 0
while True:
cds = soup.find('span', {
"id":
"feature_" + sample_info_name + "_CDS_" + str(iterator)
})
if cds == None:
break
print(cds.text)
iterator += 1
def name_collector(spl_id, spl_type):
soup = soup_collector(spl_id, spl_type)
sample_info_type = soup.findAll('a')
#unwanted till now START
try:
sample_info_name1 = sample_info_type[0].get('name').split(
'_')[1].strip()
sample_info_name2 = sample_info_type[0].get('name').split(
'_')[2].strip()
sample_info_name = sample_info_name1 + "_" + sample_info_name2
except:
sample_info_name = sample_info_type[0].get('name').split(
'_')[1].strip()
return sample_info_name
def peptide(spl_id_dup, spl_type_dup):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
iterator = 0
while True:
source = soup.find(
'span', {
"id":
"feature_" + sample_info_name + "_mat_peptide_" +
str(iterator)
})
if source == None:
break
print(source.text)
iterator += 1
def intro(spl_id, spl_type):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
try:
raw_intro = soup.findAll('a', {"name":'comment_' + sample_info_name})[0]
intro7 = raw_intro.previousSibling
intro6 = raw_intro.previousSibling.previousSibling
intro5 = raw_intro.previousSibling.previousSibling.previousSibling
intro4 = raw_intro.previousSibling.previousSibling.previousSibling.previousSibling
intro3 = raw_intro.previousSibling.previousSibling.previousSibling.previousSibling.previousSibling
intro2 = raw_intro.previousSibling.previousSibling.previousSibling.previousSibling.previousSibling.previousSibling
intro1 = raw_intro.previousSibling.previousSibling.previousSibling.previousSibling.previousSibling.previousSibling.previousSibling
intro = str(intro1) + str(intro2) + str(intro3) + str(intro4) + str(intro5) + str(intro6) + str(intro7)
return intro
except:
pass
def comment(spl_id, spl_type):
soup = soup_collector(spl_id, spl_type)
sample_info_name = name_collector(spl_id, spl_type)
try:
raw_intro = soup.find('a',
{"href": 'https://www.ncbi.nlm.nih.gov/RefSeq/'})
intro7 = raw_intro.nextSibling
intro6 = raw_intro.nextSibling.nextSibling
#intro5 = raw_intro.nextSibling.nextSibling.nextSibling
#intro4 = raw_intro.nextSibling.nextSibling.nextSibling.nextSibling
#intro3 = raw_intro.nextSibling.nextSibling.nextSibling.nextSibling.nextSibling
#intro2 = raw_intro.nextSibling.nextSibling.nextSibling.nextSibling.nextSibling.nextSibling
#intro1 = raw_intro.nextSibling.nextSibling.nextSibling.nextSibling.nextSibling.nextSibling.nextSibling
intro = str(intro7) + str(intro6)
return intro
except:
print('Oops something went wrong...')
