查找读取csv数据的起点

逐行读取文件,直到找到包含目标标头的行,然后使用 pd.read_csv() 具有 skiprows 参数开始从该行读取文件。

import pandas as pd

def find_starting_line(file_path, target_header):
    with open(file_path, 'r') as file:
        for line_num, line in enumerate(file):
            if target_header in line:
                return line_num

def read_csv_with_header(file_path, header):
    starting_line = find_starting_line(file_path, header)
    if starting_line is not None:
        return pd.read_csv(file_path, skiprows=starting_line, header=None)
    else:
        print(f"Header '{header}' not found in the file.")
        return None

# Example usage
file_path = 'your_file.csv'
header_to_find = 'Deal Type'
df = read_csv_with_header(file_path, header_to_find)
if df is not None:
    print(df)

您可能需要解析csv文件,并从您想要csv的行号中读取

import pandas as pd
def find_start_line(filename, column_name):
with open(filename, 'r') as file:
    for line_number, line in enumerate(file, 1):
        if column_name in line:
            return line_number

一旦您有了行号,请阅读csv:

int skip_num = find_start_line(file.csv,"Deal Type")
df = pd.read_csv("file.csv",skiprows=skip_num-1)
df.head()

我认为你不需要把文件读两遍。只要读一遍,跳过你不想要的行,直到你找到你的地标。

import pandas
import io

data = """
Counterparty Name
ID Number

.
.
.

Asset
USD.HO
USD.LCO
USD.RB

Cpty:
Product:

[Deal Type] [column] ... ... ...
1,2,3
4,5,6
""".strip()

with io.StringIO(data) as file_in:
    for line in file_in:
        if line.startswith("[Deal Type]"):
            break
    
    print(pandas.read_csv(file_in))