简体   繁体   中英

How can I delete the top row of my csv file using python?

My code extracts information from an xhtml file to csv. Cannot seem to delete the topmost row reading "NYSE,, ,Price,Chg,Chg". Using "del data[0]" for example gets rid of the whole column. Any help is greatly appreciated.

import sys
import re
import xml.dom.minidom

document = xml.dom.minidom.parse("2017-11-27-16-20-15.xhtml")
tableElements = document.getElementsByTagName('table')[2]

for tr in tableElements.getElementsByTagName('tr'):
data = []

for a in tr.getElementsByTagName('a'):
    for node in a.childNodes:
        if node.nodeType == node.TEXT_NODE:
            data.append(node.nodeValue)


for td in tr.getElementsByTagName('td'):
    for node in td.childNodes:
        if node.nodeType == node.TEXT_NODE:
            data.append(node.nodeValue)

del data[-1]
del data[1]
del data[1]
del data[1]

symbol = data[0]
symm = re.findall(r"\(([A-Za-z0-9_]+)\)", symbol)

sym = (''.join(symm))

company = data[0]
comp = re.sub("\(.*\)\n","", company)

volume = data[1]
lst = volume.replace(',', '')


price = data[2]
lstt = price.lstrip('$')


change = data[-1]

fullList = [sym] + [comp] + [lst] + [lstt] + [change]
fullList.insert(0, "NYSE")
print(','.join(fullList))

output pic

xhtml table(sample pic)

if data[0] return the whole column, then loop though you columns and delete the first entry.

for column in range(len(data)):
  del data[column][0]

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM