我正试图捕捉数据
here
在题为“2010年7月美国收到的价格与比较”的第二个表(大田作物)中。我使用panda dataframes从文本文件捕获表,然后将其输出到csv文件。
我的代码如下
def find_no_line_start_table(table_title,splited_data):
found_no_lines = []
for index, line in enumerate(splited_data):
if table_title in line:
found_no_lines.append(index)
return found_no_lines
def get_start_data_table(table_start, splited_data):
for index, row in enumerate(splited_data[table_start:]):
if 'Dollars' in row:
return table_start + index
def get_end_table(start_table_data, splited_data ):
for index, row in enumerate(splited_data[start_table_data:]):
if END_TABLE_LINE in row:
return start_table_data + index
def row(l):
l = l.split()
number_columns = 6
if len(l) >= number_columns:
data_row = [''] * number_columns
first_column_done = False
index = 0
for w in l:
if not first_column_done:
data_row[0] = ' '.join([data_row[0], w])
if ':' in w:
first_column_done = True
else:
index += 1
data_row[index] = w
return data_row
def take_table(txt_data):
comodity = []
q = []
w = []
e = []
t = []
p = []
for r in table:
data_row = row(r)
if data_row:
col_1, col_2, col_3, col_4, col_5, col_6 = data_row
comodity.append(col_1)
q.append(col_2)
w.append(col_3)
e.append(col_4)
t.append(col_5)
p.append(col_6)
table_data = {'comodity': comodity, 'q': q,
'w': w, 'e': e, 't': t}
return table_data
然后,我要做的是:
import requests
import pandas as pd
txt_data = requests.get("https://downloads.usda.library.cornell.edu/usda-esmis/files/c821gj76b/6w924d00c/9z903130m/AgriPric-07-30-2010.txt").text
splited_data = txt_data.split('\n')
table_title = 'Prices Received, United States'
END_TABLE_LINE = '-------------------------------------------'
_, table_start,_ = find_no_line_start_table(table_title,splited_data)
start_line = get_start_data_table(table_start, splited_data)
end_line = get_end_table(start_line, splited_data)
table = splited_data[start_line : end_line]
dict_table = take_table(txt_data)
pd.DataFrame(dict_table)
c = pd.DataFrame(dict_table)
IndexError: list assignment index out of range
但是,我这里有个错误。有谁能帮我弄清楚我做错了什么吗?
