我试过使用以下代码,但只读url和跳过列中的空格(如果有的话)是行不通的
sheet_url = df['Links']
for line in sheet_url:
#if line in sheet_url:
try:
url = line
req = requests.get(url, stream=True)
r = requests.get(url, timeout=10)
r.raise_for_status()
# checking if it is an html page
content_type = req.headers.get('content-type')
if 'html' in content_type or 'application/xhtml+xml' in content_type:
# reading the contents
html = req.content
# req.close()
output = html
print(output)
continue
else:
print("\t{} is not an HTML file".format(url))
#req.close()
except Exception:
return
请建议相同的方法/更正,谢谢
wks = gc.open_by_url(url)
wks1 = gc.open_by_url(url1)
# Defining Range of cells to read
range1 = wks1.range('A5:A9')
range2 = wks1.range('A5:B9')
range3 = wks1.range('G11:L19')
range4 = wks1.range('B12:C13')
# Defining Range of cells to write
range1n = wks.range('CO43:CS43')
range2n = wks.range('CT43:DR43')
range3n = wks.range('DS43:FK43')
range4n = wks.range('FL43:FM43')
range_names = [['range1', 'range2', 'range3', 'range4']]
for range1_cell, range1n_cell in zip(range1, range1n):
range1n_cell.value = range1_cell.value
wks.update_cells(range1n)
pandas有一个
dropna
方法来完全满足您的需要文件:^{}
在您的cas中,这可能只是相同的处理代码,第一行是:
相关问题 更多 >
编程相关推荐