def get_work_title(e, mc):
# use first work title we find in source MARC records
wt = None
for src_type, src in get_marc_src(e, mc):
if src_type == 'ia':
wt = get_ia_work_title(src)
if wt:
wt = wt.strip('. ')
if wt:
break
continue
assert src_type == 'marc'
data = None
try:
data = get_data(src)
except ValueError:
print 'bad record source:', src
print 'http://openlibrary.org' + e['key']
continue
except urllib2.HTTPError, error:
print 'HTTP error:', error.code, error.msg
print e['key']
if not data:
continue
is_marc8 = data[9] != 'a'
try:
line = get_first_tag(data, set(['240']))
except BadDictionary:
print 'bad dictionary:', src
print 'http://openlibrary.org' + e['key']
continue
if line:
wt = ' '.join(get_subfield_values(line, ['a'],
is_marc8)).strip('. ')
break
def get_work_title(e, mc):
# use first work title we find in source MARC records
wt = None
for src_type, src in get_marc_src(e, mc):
if src_type == 'ia':
wt = get_ia_work_title(src)
if wt:
wt = wt.strip('. ')
if wt:
break
continue
assert src_type == 'marc'
data = None
try:
data = get_data(src)
except ValueError:
print 'bad record source:', src
print 'http://openlibrary.org' + e['key']
continue
except urllib2.HTTPError, error:
print 'HTTP error:', error.code, error.msg
print e['key']
if not data:
continue
is_marc8 = data[9] != 'a'
try:
line = get_first_tag(data, set(['240']))
except BadDictionary:
print 'bad dictionary:', src
print 'http://openlibrary.org' + e['key']
continue
if line:
wt = ' '.join(get_subfield_values(line, ['a'], is_marc8)).strip('. ')
break
def get_work_title(e, mc):
# use first work title we find in source MARC records
wt = None
for src_type, src in get_marc_src(e, mc):
if src_type == 'ia':
wt = get_ia_work_title(src)
if wt:
wt = wt.strip('. ')
if wt:
break
continue
assert src_type == 'marc'
data = None
try:
data = get_data(src)
except ValueError:
print('bad record source:', src)
print('http://openlibrary.org' + e['key'])
continue
except urllib.error.HTTPError as error:
print('HTTP error:', error.code, error.msg)
print(e['key'])
if not data:
continue
is_marc8 = data[9] != 'a'
try:
line = get_first_tag(data, set(['240']))
except BadDictionary:
print('bad dictionary:', src)
print('http://openlibrary.org' + e['key'])
continue
if line:
wt = ' '.join(get_subfield_values(line, ['a'],
is_marc8)).strip('. ')
break
if wt:
return wt
for f in 'work_titles', 'work_title':
e_wt = e.get(f, [])
if e_wt:
assert isinstance(e_wt, list)
return e_wt[0].strip('. ')
def get_work_title(e, mc):
# use first work title we find in source MARC records
wt = None
for src_type, src in get_marc_src(e, mc):
if src_type == 'ia':
wt = get_ia_work_title(src)
if wt:
wt = wt.strip('. ')
if wt:
break
continue
assert src_type == 'marc'
data = None
try:
data = get_data(src)
except ValueError:
print('bad record source:', src)
print('http://openlibrary.org' + e['key'])
continue
except urllib2.HTTPError as error:
print('HTTP error:', error.code, error.msg)
print(e['key'])
if not data:
continue
is_marc8 = data[9] != 'a'
try:
line = get_first_tag(data, set(['240']))
except BadDictionary:
print('bad dictionary:', src)
print('http://openlibrary.org' + e['key'])
continue
if line:
wt = ' '.join(get_subfield_values(line, ['a'], is_marc8)).strip('. ')
break
if wt:
return wt
for f in 'work_titles', 'work_title':
e_wt = e.get(f, [])
if e_wt:
assert isinstance(e_wt, list)
return e_wt[0].strip('. ')
def get_work_title(e):
# use first work title we find in source MARC records
wt = None
for src_type, src in get_marc_src(e):
if src_type == 'ia':
wt = get_ia_work_title(src)
if wt:
break
continue
assert src_type == 'marc'
data = None
#print 'get from archive:', src
try:
data = get_data(src)
except ValueError:
print('bad record source:', src)
print('http://openlibrary.org' + e['key'])
continue
except urllib2.HTTPError as error:
print('HTTP error:', error.code, error.msg)
print(e['key'])
if not data:
continue
try:
line = get_first_tag(data, set(['240']))
except BadDictionary:
print('bad dictionary:', src)
print('http://openlibrary.org' + e['key'])
continue
if line:
wt = ' '.join(get_subfield_values(line, ['a'])).strip('. ')
break
if wt:
return wt
if not e.get('work_titles', []):
return
print('work title in MARC, but not in OL')
print('http://openlibrary.org' + e['key'])
return e['work_titles'][0]
def get_work_title(e):
# use first work title we find in source MARC records
wt = None
for src_type, src in get_marc_src(e):
if src_type == 'ia':
wt = get_ia_work_title(src)
if wt:
break
continue
assert src_type == 'marc'
data = None
#print 'get from archive:', src
try:
data = get_data(src)
except ValueError:
print('bad record source:', src)
print('http://openlibrary.org' + e['key'])
continue
except urllib2.HTTPError as error:
print('HTTP error:', error.code, error.msg)
print(e['key'])
if not data:
continue
try:
line = get_first_tag(data, set(['240']))
except BadDictionary:
print('bad dictionary:', src)
print('http://openlibrary.org' + e['key'])
continue
if line:
wt = ' '.join(get_subfield_values(line, ['a'])).strip('. ')
break
if wt:
return wt
if not e.get('work_titles', []):
return
print('work title in MARC, but not in OL')
print('http://openlibrary.org' + e['key'])
return e['work_titles'][0]
def get_marc_subjects(w):
for src in get_marc_source(w):
data = None
try:
data = get_data(src)
except ValueError:
print 'bad record source:', src
print 'http://openlibrary.org' + w['key']
continue
except urllib2.HTTPError, error:
print 'HTTP error:', error.code, error.msg
print 'http://openlibrary.org' + w['key']
if not data:
continue
try:
lines = list(get_tag_lines(data, subject_fields))
except BadDictionary:
print 'bad dictionary:', src
print 'http://openlibrary.org' + w['key']
continue
if lines:
yield lines
def get_marc_subjects(w):
for src in get_marc_source(w):
data = None
from openlibrary.catalog.get_ia import get_data
try:
data = get_data(src)
except ValueError:
print 'bad record source:', src
print 'http://openlibrary.org' + w['key']
continue
except urllib2.HTTPError, error:
print 'HTTP error:', error.code, error.msg
print 'http://openlibrary.org' + w['key']
if not data:
continue
try:
lines = list(get_tag_lines(data, subject_fields))
except BadDictionary:
print 'bad dictionary:', src
print 'http://openlibrary.org' + w['key']
continue
if lines:
yield lines
def get_marc_subjects(w):
for src in get_marc_source(w):
data = None
from openlibrary.catalog.get_ia import get_data
try:
data = get_data(src)
except ValueError:
print('bad record source:', src)
print('http://openlibrary.org' + w['key'])
continue
except urllib2.HTTPError as error:
print('HTTP error:', error.code, error.msg)
print('http://openlibrary.org' + w['key'])
if not data:
continue
try:
lines = list(get_tag_lines(data, subject_fields))
except BadDictionary:
print('bad dictionary:', src)
print('http://openlibrary.org' + w['key'])
continue
if lines:
yield lines
def read_works():
i = 0
pages = {}
page_marc = {}
for work, marc in work_and_marc():
lines = []
for loc in marc:
data = get_data(loc)
if not data:
continue
found = [v for k, v in get_tag_lines(data, set(['600']))]
if found:
lines.append((loc, found))
if not lines:
continue
work['lines'] = lines
i += 1
print(i, work['key'], work['title'])
try:
people, marc_alt = read_people(j[1] for j in lines)
except AssertionError:
print(work['lines'])
continue
except KeyError:
print(work['lines'])
continue
marc_alt_reverse = defaultdict(set)
for k, v in marc_alt.items():
marc_alt_reverse[v].add(k)
w = ol.get(work['key'])
w['subject_people'] = []
for p, num in people.iteritems():
print(' %2d %s' % (num, ' '.join("%s: %s" % (k, v) for k, v in p)))
print(' ', p)
if p in page_marc:
w['subject_people'].append({'key': '/subjects/people/' + page_marc[p]})
continue
obj = build_person_object(p, marc_alt_reverse.get(p, []))
key = obj['name'].replace(' ', '_')
full_key = '/subjects/people/' + key
w['subject_people'].append({'key': full_key})
if key in pages:
print(key)
pages[key]['marc'].append(p)
continue
for m in obj['marc']:
page_marc[m] = key
pages[key] = obj
obj_for_db = obj.copy()
del obj_for_db['marc']
obj_for_db['key'] = full_key
obj_for_db['type'] = '/type/person'
print(ol.save(full_key.encode('utf-8'), obj_for_db, 'create a new person page'))
print(w)
print(ol.save(w['key'], w, 'add links to people that this work is about'))
def read_works():
i = 0
pages = {}
page_marc = {}
for work, marc in work_and_marc():
lines = []
for loc in marc:
data = get_data(loc)
if not data:
continue
found = [v for k, v in get_tag_lines(data, set(['600']))]
if found:
lines.append((loc, found))
if not lines:
continue
work['lines'] = lines
i += 1
print i, work['key'], work['title']
try:
people, marc_alt = read_people(j[1] for j in lines)
except AssertionError:
print work['lines']
continue
except KeyError:
print work['lines']
continue
marc_alt_reverse = defaultdict(set)
for k, v in marc_alt.items():
marc_alt_reverse[v].add(k)
w = ol.get(work['key'])
w['subject_people'] = []
for p, num in people.iteritems():
print ' %2d %s' % (num, ' '.join("%s: %s" % (k, v) for k, v in p))
print ' ', p
if p in page_marc:
w['subject_people'].append({'key': '/subjects/people/' + page_marc[p]})
continue
obj = build_person_object(p, marc_alt_reverse.get(p, []))
key = obj['name'].replace(' ', '_')
full_key = '/subjects/people/' + key
w['subject_people'].append({'key': full_key})
if key in pages:
print key
pages[key]['marc'].append(p)
continue
for m in obj['marc']:
page_marc[m] = key
pages[key] = obj
obj_for_db = obj.copy()
del obj_for_db['marc']
obj_for_db['key'] = full_key
obj_for_db['type'] = '/type/person'
print ol.save(full_key.encode('utf-8'), obj_for_db, 'create a new person page')
print w
print ol.save(w['key'], w, 'add links to people that this work is about')
