python 获取页面表格数据存放到csv中的方法
获取单独一个table，代码如下：
#!/usr/bin/envpython3
#_*_coding=utf-8_*_
importcsv
fromurllib.requestimporturlopen
frombs4importBeautifulSoup
fromurllib.requestimportHTTPError
try:
html=urlopen("http://en.wikipedia.org/wiki/Comparison_of_text_editors")
exceptHTTPErrorase:
print("notfound")
bsObj=BeautifulSoup(html,"html.parser")
table=bsObj.findAll("table",{"class":"wikitable"})[0]
iftableisNone:
print("notable");
exit(1)
rows=table.findAll("tr")
csvFile=open("editors.csv",'wt',newline='',encoding='utf-8')
writer=csv.writer(csvFile)
try:
forrowinrows:
csvRow=[]
forcellinrow.findAll(['td','th']):
csvRow.append(cell.get_text())
writer.writerow(csvRow)
finally:
csvFile.close()
获取所有table，代码如下：
#!/usr/bin/envpython3
#_*_coding=utf-8_*_
importcsv
fromurllib.requestimporturlopen
frombs4importBeautifulSoup
fromurllib.requestimportHTTPError
try:
html=urlopen("http://en.wikipedia.org/wiki/Comparison_of_text_editors")
exceptHTTPErrorase:
print("notfound")
bsObj=BeautifulSoup(html,"html.parser")
tables=bsObj.findAll("table",{"class":"wikitable"})
iftablesisNone:
print("notable");
exit(1)
i=1
fortableintables:
fileName="table%s.csv"%i
rows=table.findAll("tr")
csvFile=open(fileName,'wt',newline='',encoding='utf-8')
writer=csv.writer(csvFile)
try:
forrowinrows:
csvRow=[]
forcellinrow.findAll(['td','th']):
csvRow.append(cell.get_text())
writer.writerow(csvRow)
finally:
csvFile.close()
i+=1
以上这篇python获取页面表格数据存放到csv中的方法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持毛票票。