问如何使用pandas从txt加载数据？

EN

import pandas as pd
from io import StringIO

mystr = StringIO("""product/productId: B003AI2VGA
review/userId: A141HP4LYPWMSR
review/profileName: Brian E. Erland "Rainbow Sphinx"
review/helpfulness: 7/7
review/score: 3.0
review/time: 1182729600
review/summary: "There Is So Much Darkness Now ~ Come For The Miracle"
review/text: Synopsis: On the daily trek from Juarez, Mexico to ... 

product/productId: B003AI2VGA
review/userId: A328S9RN3U5M68
review/profileName: Grady Harp
review/helpfulness: 4/4
review/score: 3.0
review/time: 1181952000
review/summary: Worthwhile and Important Story Hampered by Poor Script and Production
review/text: THE VIRGIN OF JUAREZ is based on true events...""")

# replace mystr with 'file.txt'
df = pd.read_csv(mystr, header=None, sep='|', error_bad_lines=False)

df = pd.DataFrame(df[0].str.split(':', n=1).values.tolist())
df = df.loc[df[0].isin({'review/text', 'review/score'})]

               0                                                  1
4   review/score                                                3.0
7    review/text   Synopsis: On the daily trek from Juarez, Mexi...
12  review/score                                                3.0
15   review/text    THE VIRGIN OF JUAREZ is based on true events...

with open('your_text_file.txt') as f:
    text_lines = f.readlines()

# create pandas Series object where each value is a text line from your file
s = pd.Series(text_lines)

# remove the new-lines
s = s.str.strip()

# extract some columns using regex and represent in a dataframe
df = s.str.split('\s?(.*)/([^:]*):(.*)', expand=True)

# remove irrelevant columns
df = df.replace('', np.nan).dropna(how='all', axis=1)

def gb_organize(df_):
    """
    Organize a sub-dataframe from group-by operation.
    """
    df_ = df_.dropna()
    return pd.DataFrame(df_[3].values, index=df_[2].values).T

# pass a Series object to .groupby to iterate over consecutive non-null rows
df_result = df.groupby(df.isna().all(axis=1).cumsum(), group_keys=False).apply(gb_organize)

df_result = df_result.set_index(['productId', 'userId'])

# then you can access the records you want with the following:
df_result[['score', 'text']]