def fix_it(timestamp, book_chapter, content_err_list, content_fix_list):
fix_dir = '../data/{}.fix'.format(timestamp)
os.makedirs(fix_dir, exist_ok=True)
fin_json = '../data/{}/{}.json'.format(timestamp, book_chapter)
fold_json = '{}/{}.old.json'.format(fix_dir, book_chapter)
fnew_json = '{}/{}.new.json'.format(fix_dir, book_chapter)
data = utils.load_json(fin_json)
new_content = []
content_changed = False
for i, x in enumerate(data['content']):
has_issue = False
for y, zz in zip(content_err_list, content_fix_list):
if (x['vers'] == y['vers'] and x['text'] == y['text']):
has_issue = True
for z in zz:
new_content.append(z)
content_changed = True
if not has_issue:
new_content.append(x)
if not content_changed:
print(':: target problem is not found in {}'.format(fin_json),
file=sys.stderr,
flush=True)
return
qcmd('cp {} {}'.format(fin_json, fold_json))
data['content'] = new_content
utils.write_json(data, fnew_json)
qcmd('cp {} {}'.format(fnew_json, fin_json))
def get_chapter_text(in_url, out_json, tsleep):
data = {}
error = None
if os.path.isfile(out_json):
return data, error
try:
utils.qprint('get ' + in_url)
r = requests.get(in_url)
if not r.ok:
raise Exception('can not get url ' + in_url)
time.sleep(tsleep)
text = etree.HTML(r.text)
data['url'] = in_url
pattern = (r'<span class="chapter_title"> (.*?) <i class="glyphicon '
'glyphicon-chevron-right "> </i> (.*?) <i class="glyphicon '
'glyphicon-chevron-right"> </i> (.*?)</span>')
x = re.findall(pattern, r.text)
if x:
data['volume'] = x[0][0]
data['book'] = x[0][1]
data['chapter'] = x[0][2]
else:
data['volume'] = None
data['book'] = None
data['chapter'] = None
phrase_set = set()
data['content'] = []
for x in text.xpath('//div[@id="bible_chapter_content"]/*'):
t = {'vers': None, 'text': None}
if x.tag == 'p':
t = {'vers': x.get('value'), 'text': x.text.split(' ', 1)[-1]}
else:
t = {'vers': '', 'text': x.text}
if t['vers'] == None and t['text'] == None:
raise Exception(
'can not extract content from "{}" (url={})'.format(
x.text, in_url))
# avoid duplicate entry
phrase = '|{}|{}|'.format(t['vers'], t['text'])
if phrase not in phrase_set:
data['content'].append(t)
phrase_set.add(phrase)
utils.write_json(data, out_json)
data = {}
except Exception as e:
error = '*ERROR* ' + str(e)
raise
data = {}
return data, error
def get_chapter_text(in_url, out_json, tsleep):
data = {}
error = None
# if os.path.isfile(out_json):
# return data, error
try:
utils.qprint('get ' + in_url)
r = requests.get(in_url)
if not r.ok:
raise Exception('can not get url ' + in_url)
time.sleep(tsleep)
text = etree.HTML(r.text)
data['url'] = in_url
x = text.xpath('//div[@class="libro"]')
data['book'] = x[0].text if x else None
x = text.xpath('//div[@id="capitolo"]')
data['chapter'] = x[0].text.strip() if x else None
data['content'] = []
el = text.xpath('//div[@class="testidellibro"]')[0]
s = html.unescape(etree.tostring(el).decode('utf-8'))
for line in s.split('\n'):
if not line.startswith('<sup>'):
continue
# x = re.findall(r'<sup>.*?<a .*?>(.*?)</a></sup>(.*?)$', line)
x = re.findall(r'<a (.*?)>(.*?)</a></sup>(.*?)$', line)
if not x:
continue
atag, vers, phrase = x[0]
vers = re.findall(r'name="VER_(.*?)"', atag)[0]
phrase = re.sub(r'<.*?>', ' ', phrase)
phrase = re.sub(r'\t', ' ', phrase)
phrase = re.sub(r' +', ' ', phrase)
t = {'vers': vers, 'text': phrase.strip()}
data['content'].append(t)
utils.write_json(data, out_json)
data = {}
except Exception as e:
error = '*ERROR* ' + str(e)
raise
data = {}
return data, error
def get_all_chapter_links(out_json, tsleep=1, nproc=3, nretry=10):
data = []
args_list = []
for i in range(1, 74):
url = '{}/index.php/?m=bible&template={}'.format(host, i)
args_list.append([url, tsleep])
tmp = utils.parallel_call(get_chapter_links,
args_list,
nproc=nproc,
nretry=nretry)
for x in tmp:
for y in x:
data.append(y)
utils.write_json(data, out_json)
return data
def get_journal_data(in_url, out_json, tsleep):
'''Get journal data (name, issn, impact factors) from input URL
https://www.scijournal.org/impact-factor-of-ACM-SIGPLAN-NOTICES.shtml
and get URL of next/previous journals
'''
data = {}
error = None
if os.path.isfile(out_json):
return data, error
try:
utils.qprint('get ' + in_url)
r = requests.get(in_url)
if not r.ok:
raise
time.sleep(tsleep)
root = etree.HTML(r.text)
data = {}
data['url'] = in_url
x = root.xpath('//h1')[0].text
data['title'] = x.replace('Impact Factor','').strip()
x = re.findall(r'Journal Abbreviation: (.*?)<br>', r.text)
data['title_abbrev'] = x[0] if x else None
x = re.findall('Journal ISSN: (.*?)$', r.text, re.MULTILINE)
data['issn'] = x[0] if x else None
data['impact'] = {}
years = ['2016/2017']
for i in range(2008, 2016):
years.append(str(i))
for year in years:
x = re.findall(r'{} Impact Factor : (.*?)<br>'.format(year), r.text)
data['impact'][year] = x[0] if x else '-NA-'
utils.write_json(data, out_json)
except Exception as e:
error = '*ERROR* ' + str(e)
data = {}
return data, error
def get_all_chapter_links(out_json, tsleep=1, nproc=3, nretry=10):
data = []
args_list = []
for i in range(1, 74):
url = ('{}/pls/labibbia_new/Bibbia_Utils.elenco_capitoli?'
'origine=cei2008&idlibroz={}'.format(host, i))
args_list.append([url, tsleep])
tmp = utils.parallel_call(get_chapter_links,
args_list,
nproc=nproc,
nretry=nretry)
for x in tmp:
for y in x:
data.append(y)
utils.write_json(data, out_json)
return data
def test():
# data, error = get_journal_links(
# # 'https://www.scijournal.org/list-of-impact-factor-journal_Z.shtml',
# 'https://www.scijournal.org/agriculture-and-forestry-journal-impact-factor-list.shtml',
# 0)
# url = 'https://www.scijournal.org/impact-factor-of-NAT-REV-CANCER.shtml'
# url = 'https://www.scijournal.org/impact-factor-of-HEALTH-INFORM-J.shtml'
# data, error = get_journal_data(
# url,
# # 'https://www.scijournal.org/impact-factor-of-NATURE.shtml',
# 'foo.json', 0)
# print(json.dumps(data, sort_keys=True, indent=2))
# print(len(data))
# print(error)
data = get_all_journal_links(nproc=3, nretry=10, tsleep=1)
utils.write_json(data, 'foo.json')
def get_data(oid, out_json, proxy_set, tsleep):
'''input Ontology ID, output in ../data
'''
if os.path.isfile(out_json):
return None, None
out_dir = abspath(dirname(out_json))
os.makedirs(out_dir, exist_ok=True)
proxies = None
if len(proxy_set):
proxy = random.choice(list(proxy_set))
proxies = {'http': proxy}
headers = {
'User-Agent': ('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/39.0.2171.95 Safari/537.36'),
'Authorization':
token,
}
timeout_connect = 10
timeout_read = 30
timeout = (timeout_connect, timeout_read)
# need to change
url = None
if oid.startswith('HP:'):
url = host + '/hpo/?search={}&type=0&page=1'.format(oid)
elif oid.startswith('OMIM:'):
oid = oid.split(':')[1]
url = host + '/omim/?search={}&type=1&page=1'.format(oid)
else:
raise 'input ID is not HP or OMIM'
data = dict()
error = None
try:
utils.qprint('get ' + url)
r = requests.get(url,
headers=headers,
proxies=proxies,
timeout=timeout)
time.sleep(tsleep)
if not r.ok:
raise 'can not get url: ' + url
data = json.loads(r.text)
if len(data) != 4:
raise 'output json seems incorrect (missing keys)'
utils.write_json(data, out_json)
except Exception as e:
error = '*ERROR* ' + str(e)
data = dict()
# print(error)
# raise
return None, error
def get_journal_data(in_url, out_json, tsleep):
'''Get journal data (name, issn, impact factors) from input URL
http://www.bioxbio.com/if/html/{journal}.html
and get URL of next/previous journals
'''
data = {'done': [], 'todo': []}
error = None
try:
utils.qprint('get ' + in_url)
r = requests.get(in_url)
if not r.ok:
raise
time.sleep(tsleep)
root = etree.HTML(r.text)
if not os.path.isfile(out_json):
jdata = {}
jdata['url'] = in_url
jdata['title'] = root.xpath('//div/h1')[0].text
x = re.findall(r'<p>Journal Abbreviation: (.*?)<br>', r.text)
jdata['title_abbrev'] = x[0] if x else x
x = re.findall(r'Journal ISSN: (.*?)</p>', r.text)
jdata['issn'] = x[0] if x else x
jdata['impact'] = {}
for tr in root.xpath('//table/tr'):
td_list = tr.xpath('./td')
if len(td_list) != 3:
continue
year, ifact, npub = [x.text for x in td_list]
if year == 'Year':
continue
try:
ifact = float(ifact)
except:
ifact = -1
try:
npub = int(npub)
except:
npub = -1
jdata['impact'][year] = {
'ifact': ifact,
'npub': npub,
}
utils.write_json(jdata, out_json)
data['done'].append(in_url)
# get prev and next url
a = root.xpath('//div[@class="col-md-6 col-sm-12 text-left"]/a')
data['todo'].append('http://www.bioxbio.com/if/html/' +
a[0].get('href'))
a = root.xpath('//div[@class="col-md-6 col-sm-12 text-right"]/a')
data['todo'].append('http://www.bioxbio.com/if/html/' +
a[0].get('href'))
except Exception as e:
error = '*ERROR* ' + str(e)
data = []
return data, error
def test():
data, error = get_journal_data(
'http://www.bioxbio.com/if/html/Z-PADAGOGIK.html', 'foo.json', 0)
print(data)
print(error)
if __name__ == '__main__':
# timestamp = '201804140057'
# catch_missing(timestamp)
# test()
if len(sys.argv) != 2:
timestamp = utils.get_timestamp()
else:
timestamp = sys.argv[1]
out_dir = '../data/{}'.format(timestamp)
subject_json = '../data/{}.subject.json'.format(timestamp)
data = {}
if os.path.isfile(subject_json):
data = utils.load_json(subject_json)
else:
data = get_all_journal_links()
utils.write_json(data, subject_json)
get_all_journal_data(data, out_dir)
# print(json.dumps(data, sort_keys=True, indent=2))
# print(len(data))
# print(error)
data = get_all_journal_links(nproc=3, nretry=10, tsleep=1)
utils.write_json(data, 'foo.json')
if __name__ == '__main__':
# test()
if len(sys.argv) != 2:
timestamp = utils.get_timestamp()
else:
timestamp = sys.argv[1]
out_dir = '../data/{}'.format(timestamp)
url_json = '../data/{}.url.json'.format(timestamp)
data = {}
if os.path.isfile(url_json):
data = utils.load_json(url_json)
else:
data = get_all_journal_links()
utils.write_json(data, url_json)
get_all_journal_data(data, out_dir)
