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/env python3
# _*_ coding=utf-8 _*_
import csv
from urllib.request import urlopen
from bs4 import beautifulsoup
from urllib.request import httperror
try:
  html = urlopen("http://en.wikipedia.org/wiki/comparison_of_text_editors")
except httperror as e:
  print("not found")
bsobj = beautifulsoup(html,"html.parser")
table = bsobj.findall("table",{"class":"wikitable"})[0]
if table is none:
  print("no table");
  exit(1)
rows = table.findall("tr")
csvfile = open("editors.csv",'wt',newline='',encoding='utf-8')
writer = csv.writer(csvfile)
try:
  for row in rows:
    csvrow = []
    for cell in row.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/env python3
# _*_ coding=utf-8 _*_
import csv
from urllib.request import urlopen
from bs4 import beautifulsoup
from urllib.request import httperror
try:
  html = urlopen("http://en.wikipedia.org/wiki/comparison_of_text_editors")
except httperror as e:
  print("not found")
bsobj = beautifulsoup(html,"html.parser")
tables = bsobj.findall("table",{"class":"wikitable"})
if tables is none:
  print("no table");
  exit(1)
i = 1
for table in tables:
  filename = "table%s.csv" % i
  rows = table.findall("tr")
  csvfile = open(filename,'wt',newline='',encoding='utf-8')
  writer = csv.writer(csvfile)
  try:
    for row in rows:
      csvrow = []
      for cell in row.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。