python 在单独的列中给出列名和写入值作为表

Question

我的代码

from lxml import html
import requests
import csv
# encoding=utf8
import sys
reload(sys)
sys.setdefaultencoding('utf8')


# example site
page = requests.get('http://www.wintergreenfund.com/reports/top-ten/')
tree = html.fromstring(page.text)
#This will create a list of services:

tname = tree.xpath('//*[@id="colLeft"]//table//tr/td[1]/text()')
tvalue = tree.xpath('//table//tr/td[2]/text()')



print tname
print tvalue

print 'Input the csv file'
csvfile = raw_input("> ")

res = tname,tvalue


#Assuming res is a list of lists
with open(csvfile, "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    writer.writerows(res)

我在 csv 中的输出

Reynolds American Inc. Consolidated-Tomoka Land Co. British American Tobacco

8.30% 7.50% 7.10% 6.60% 6.40% 5.90% 5.30% 4.80% 4.70% 4.10%

要求的输出与具有列名的网站相同

引用 http://www.wintergreenfund.com/reports/top-ten/

而且 unicode 也不起作用。需要这方面的帮助

我的新代码

from lxml import html
import requests
import csv

page = requests.get('http://www.wintergreenfund.com/reports/top-ten/')
tree = html.fromstring(page.text)

csvrows = []
for rows in tree.xpath('//*[@id="colLeft"]//table//tr'):
    csvrows.append([rows.xpath('./td[1]/text()'),rows.xpath('./td[2]/text()')])
print csvrows
print 'Input the csv file'
csvfile = raw_input("> ")
with open(csvfile, "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    writer.writerow(['Name','Value']) #substitute as appropriate.
    writer.writerows(csvrows)

我在其中获得了 [' '] 的值(value)，并且 [ ] 也是空的

Answer 1

首先，如果你想在每个相应的索引处组合两个列表，你应该使用 zip() ，目前你正在创建一个包含两个列表的元组 - res = tname ,tvalue - 然后将其按原样写入 csv。

此外，其次，您应该首先使用 xpath 获取表中的每一行，然后使用 xpath 从中获取每个必需的 td 元素。而不是像您当前使用的那样使用两个 xpath。

例子-

from lxml import html
import requests
import csv

page = requests.get('http://www.wintergreenfund.com/reports/top-ten/')
tree = html.fromstring(page.text)

csvrows = []
for rows in tree.xpath('//*[@id="colLeft"]//table//tr'):
    row1text = rows.xpath('./td[1]/text()')
    row2text = rows.xpath('./td[2]/text()')
    if row1text and row2text:
        csvrows.append([row1text[0],row2text[0]])
print(csvrows)
print('Input the csv file')
csvfile = input("> ")
with open(csvfile, "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    writer.writerow(['Name','Value']) #substitute as appropriate.
    writer.writerows(csvrows)