|
|
@ -96,7 +96,8 @@ def ref_str2dic(text):
|
|
|
|
if not re.match(r'\d{4}', py):
|
|
|
|
if not re.match(r'\d{4}', py):
|
|
|
|
py = None
|
|
|
|
py = None
|
|
|
|
doi_idx = ref.find(DOI_SPLIT_SYMBOL)
|
|
|
|
doi_idx = ref.find(DOI_SPLIT_SYMBOL)
|
|
|
|
model = dict(au=au, py=py, so=so)
|
|
|
|
# 把参考文献字段也加进去
|
|
|
|
|
|
|
|
model = dict(au=au, py=py, so=so, ref=ref)
|
|
|
|
if doi_idx != -1:
|
|
|
|
if doi_idx != -1:
|
|
|
|
doi_text = ref[doi_idx + DOI_SPLIT_SYMBOL_LENGTH:]
|
|
|
|
doi_text = ref[doi_idx + DOI_SPLIT_SYMBOL_LENGTH:]
|
|
|
|
if doi_text.startswith('['):
|
|
|
|
if doi_text.startswith('['):
|
|
|
@ -226,9 +227,9 @@ def step_2_1(table: pd.DataFrame, ai_result_table):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main_step1():
|
|
|
|
def main_step1():
|
|
|
|
# step_1_1()
|
|
|
|
step_1_1()
|
|
|
|
# step_1_2()
|
|
|
|
# step_1_2()
|
|
|
|
step_1_3() # WOS:000426769900009
|
|
|
|
# step_1_3() # WOS:000426769900009
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main_step2():
|
|
|
|
def main_step2():
|
|
|
@ -249,5 +250,5 @@ def main_step2():
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
if __name__ == '__main__':
|
|
|
|
# main_step1()
|
|
|
|
main_step1()
|
|
|
|
main_step2()
|
|
|
|
# main_step2()
|
|
|
|