python 获取页面表格数据存放到csv中的方法

时间:2022-11-09 23:53:40

获取单独一个table,代码如下:

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
#!/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:

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
#!/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服务器之家。

原文链接:https://blog.csdn.net/u011085172/article/details/73810708