python - 如何通过在python中调用文件中的函数名来打印文件名
问题描述
这是一个基于简历筛选的程序。在这个程序中,我为每个 CV 打分以对它们进行排名。现在输出只是给了我我想要的分数,它给了我文件名。该程序是:
import re
import fitz
import os
# Create an array "zs[]" that store the score values
zs = []
# call the Resume files by calling the folder name
for filename in os.listdir('resume/'):
# Select only PDF files
if filename.endswith('.pdf'):
print(filename)
os.chdir('C:/Users/M. Abrar Hussain/Desktop/cv/resume')
pdfFileObj = open(filename, 'rb')
# Extract the text Data from resume files
with fitz.open(pdfFileObj) as doc:
text = ""
for page in doc:
text += page.getText()
print(text)
# Splitting the Resume Data into many indexes of Array
p = doc.loadPage(0)
p_text = p.getText()
p_lines = p_text.splitlines()
# Split the information and the data
split_lst = [i.split(': ', 1) for i in p_lines]
d = {a: b.rstrip() for a, b in split_lst}
# Naming the information part
f = d["Name"]
g = d["GPA"]
h = d["Skills"]
i = d["Experience"]
p = re.findall(r"[-+]?\d*\.\d+|\d+", i)
# search the keywords with the data that extract from resume
search_keywords = ['Laravel', 'Java', 'Python']
search_exp = ['1', '1.5', '2', '2.5', '3']
search_gpa = ['2.5', '2.6', '2.7', '2.8', '2.9', '3.0', '3.1', '3.2', '3.3', '3.4', '3.5', '3.6', '3.7',
'3.8', '3.9', '4.0']
# Comparing GPA data with the keywords
lst = []
for gpa in search_gpa:
if gpa in g:
lst.append(gpa)
# Comparing Skills data with keywords
lst1 = []
for word in search_keywords:
if word in h:
lst1.append(word)
# Comparing Experience data with keywords
lst2 = []
for exp in search_exp:
if exp in p:
lst2.append(exp)
# Scoring the Extracted data to see the best resume
score = 0
w1 = []
# Scoring the GPA
for w1 in lst:
if '3.0' <= w1 < '3.5':
score += 1
if '3.5' <= w1 <= '4':
score += 2
# Scoring the SKills
for w1 in lst1:
if w1 == 'Laravel':
score += 2
if w1 == 'Python':
score += 2
if w1 == 'Java':
score += 1
# Scoring the Experience
for w1 in lst2:
if '2.5' <= w1 < '3':
score += 0.5
if '3' <= w1 < '3.5':
score += 1
if '3.5' <= w1:
score += 2
# store score values in an array
tt = zs.append(score)
print("%s has Scored %s" % (f, score))
print('\n')
pdfFileObj.close()
# Rank the CV's on the basis of Scoring
zs.sort(reverse=True)
print(zs)
程序的输出是:
cv2.pdf
Name: Danish Ejaz
GPA: 3.7
Skills: Python, Java
Experience: 2.5 years
Danish Ejaz has Scored 5.5
cv3.pdf
Name: Abdullah
GPA: 3.2
Skills: Laravel, Java
Experience: 2 years
Abdullah has Scored 4
cv5.pdf
Name: M. Abrar Hussain
GPA: 3.5
Skills: Python, Laravel
Experience: 3 years
M. Abrar Hussain has Scored 7
[7, 5.5, 4]
Process finished with exit code 0
倒数第二行是计分后的结果。在这个结果中,它只是给了我们得分号,我也可以在结果中调用文件名吗?如果是,请帮助我完成这个项目。
解决方案
您只需要存储文件名并在最后将它们与分数一起打印:
# Create a dictionary with filenames as key and add the score as value
# Note that this might be an issue if you have irrelevant files in your directory
file_scores = dict.fromkeys(listdir('resume/'))
# call the Resume files by calling the folder name
for filename in file_scores:
# Your scoring logic
(...)
# store score values in the dictionary
file_scores[filename] = score
(...)
# Remove items without value
file_scores = {k: v for k, v in file_scores.items() if v}
# Sort the dictionary based on score descending
file_scores = {k: v for k, v in sorted(file_scores.items(), key=lambda x: x[1], reverse=True)}
# Print the file and the score together
for filename, score in file_scores.items():
if score: # Ignore other files
print(f"File {filename}: Score = {score}")
推荐阅读
- apache-spark - 在 EMR 上的 PySpark 中运行自定义 Java 类
- amazon-web-services - 如何授予我上传的 aws lambda 函数的权限?
- javascript - Node.js SQL 如何运行跨越两个数据库的查询
- python - 列表中小于或等于 k 的最大非连续值总和
- math - 你如何为两个圆的维恩图的并集、交集和乘积编写伪代码?
- pandas - 只保留一个值的第一次出现,直到它更改为另一个值
- regex - 正则表达式匹配字符串中的所有斜杠,如果单词出现在字符串中的任何位置
- spring - 身份验证提供程序 Spring Security 5
- android - Kotlin 实例化异常
- javascript - jQuery选择带有变量的多个项目