python 获取页面表格数据存放到csv中

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




你可能感兴趣的:(python)