read_url = urllib.request.urlopen('your_sheet_url').read() #read the url
data = BeautifulSoup(read_url,"html.parser")
table = data.table #extract table
output_rows = []
df = pd.DataFrame(columns=['State','','Confirmed','Recovered','Deaths','Active','Last_Updated_Time'])
for table_row in table.findAll('tr'): #iterate though rows
columns = table_row.findAll('td')
output_row = []
for column in columns: #iterate though columns
print(column.text)
output_row.append(column.text) #append into a list
print(len(output_row))
output_rows.append(output_row)
try:
df = df.append(pd.Series(output_row,index = df.columns.tolist()),ignore_index = True) #add to the final dataframe
except:
pass
df.toexcel("Output.xlsx") # save the datafram as excel file
您尝试使用的漂亮的汤法将以这种方式工作
您可以使用
google-api-python-client
有一个快速启动文档可用here
它可以归结为这样的东西:
但一定要阅读完整的快速入门,以获得完整的图片。(示例代码取自此处。)
相关问题 更多 >
编程相关推荐