table = soup.find('table', attrs={'id':'MainContent_grdUsers2'})
data = []
for tr in table.find_all('tr')[1:] :
td = tr.find_all('td')
try :
data += [
[
td[0].getText() ,
td[2].find('option', {'selected':'selected'}).getText(),
td[3].find('option', {'selected':'selected'}).getText(),
td[4].find('input').get('value'),
td[5].find('input').get('value'),
td[6].find('option', {'selected':'selected'}).getText()
]
]
except Exception as ex :
print(ex)
continue
with open('test5.csv', 'w', newline='') as outfile:
writer = csv.writer(outfile)
for row in data :
writer.writerow([' '.join(str(r) for r in row)])
我正在尝试将复杂的html表解析为csv。此代码工作并获取所需数据,但每行包含在一个单元格中,而不是每行6个值中的每一个都包含单独的列。我在这做错了什么?
答案 0 :(得分:1)
您不必要地设置newline=''
并使用空格连接表格单元格。您的数据似乎采用合适的格式直接传递给writer.writerows()
。
with open('test5.csv', 'w') as outfile:
writer = csv.writer(outfile)
header = ['Name', 'Rights', 'Bureaus', 'FullName', 'Email', 'Status']
writer.writerow(header)
writer.writerows(data)