基金申请-4：如何检索国家基金科研项目？

检索网站

https://journal.medsci.cn/m/nsfc.do
https://www.medsci.cn/sci/nsfc_index
保存源码到c.txt

提取检索信息

# -*- coding: utf-8 -*-

import pandas as pd
import re 


def ifind(somestr,sub):
    s = [substr.start() for substr in re.finditer(sub , somestr)]
    return s

def find2(txt,str1,str2):    
    s = ifind(txt,str1)
    # print(txt)
    
    if(len(txt)>300):
        txt1 = txt[s[0]+len(str1):s[0]+300]
    else:
        txt1 = txt[s[0]+len(str1):]
    k = txt1.find(str2)
    txt1 = txt1[:k]
    return txt1

file = 'c.txt'
f = open(file,encoding='utf-8', errors='ignore')
txt = f.read()
f.close() 

# print(txt)

str1 = '<dd data-label="项目名">'
str2 = '<dd data-label="负责人">'
str3 = 'target="_blank">'
str4 = '</a>'
s = ifind(txt,str1)
# print(s)

numRows = len(s)
numCols = 10
d = pd.DataFrame(index=range(numRows),columns=range(numCols))

m=0
for k in s:
    txt1 = find2(txt[k:],str1,str2)
    txt2 = find2(txt1,str3,str4)
    print(txt2)
    d.iloc[m,0]=txt2
    m=m+1
# print(k)

str1 = '<dd data-label="依托单位">'
str2 = '<dd data-label="经费">'
str3 = 'action=q&txtitle='
str4 = '" target="_blank">'
# s = ifind(txt,str1)
m=0
for k in s:
    txt1 = find2(txt[k:],str1,str2)
    txt2 = find2(txt1,str3,str4)
    d.iloc[m,1]=txt2
    m=m+1
# print(k)

str1 = '<dd data-label="负责人">'
str2 = '<dd data-label="依托单位>'
str4 = '</dd>'
s = ifind(txt,str1)
print(s)
m=0
for k in s:
    txt1 = find2(txt[k:],str1,str2)
    txt1 = txt1[:10]
    # print(txt1)
    k1 = txt1.find(str4)
    txt1=txt1[:k1]
    print(txt1)
    d.iloc[m,2]=txt1
    m=m+1
# print(k)

str1 = '<dd data-label="起始时间">'
str2 = '<dl class="dl">'
str3 = '<dd data-label="基金">'
str4 = '</dd>'
s = ifind(txt,str1)
# print(s)
m=0
for k in s:
    txt1 = find2(txt[k:],str1,str2)
    txt2 = find2(txt[k:],str3,str4)
    txt1 = txt1[:30]
    # print(txt1)
    k1 = txt1.find(str4)
    txt1=txt1[:k1]
    # if(m==0):
    #     print(txt2)
    d.iloc[m,3]=txt1
    d.iloc[m,4]=txt2
    m=m+1
# print(k)

str1 = '<dd data-label="代码">'
str2 = '<dd data-label="项目名">'
str3 = '<dd data-label="基金">'
str4 = '</dd>'
s = ifind(txt,str1)
# print(s)
m=0
for k in s:
    txt1 = find2(txt[k:],str1,str2)
    # txt2 = find2(txt[k:],str3,str4)
    txt1 = txt1[:30]
    # print(txt1)
    k1 = txt1.find(str4)
    txt1=txt1[:k1]
    print(txt1)
    # if(m==0):
    #     print(txt2)
    # d.iloc[m,3]=txt1
    d.iloc[m,5]=txt1
    m=m+1
# print(k)


str1 = '<dd data-label="经费">'
str2 = '<dd data-label="起始时间">'
str3 = '<dd data-label="基金">'
str4 = '</dd>'
s = ifind(txt,str1)
# print(s)
m=0
for k in s:
    txt1 = find2(txt[k:],str1,str2)
    # txt2 = find2(txt[k:],str3,str4)
    txt1 = txt1[:30]
    # print(txt1)
    k1 = txt1.find(str4)
    txt1=txt1[:k1]
    print(txt1)
    # if(m==0):
    #     print(txt2)
    # d.iloc[m,3]=txt1
    d.iloc[m,6]=txt1
    m=m+1
# print(k)

d.to_csv(file+'out.csv',index=1,header=1,encoding='UTF-8-sig')

结果在c.txtout.csv