Python3 多种方式爬取最新30期双色球历史数据存入csv

双色球这个页面有点坑，首先是https加密链接，然后主要的是，他们页面可能编码不是用的常用编码，

用urllib的urlopen方法爬取下来的内容貌似16进制码，如下：

b'\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\x03\xad[\xdb\x8e\x1b\xc7\x11}\x96\xbf\x82a\x90\xc0\x02f\xb3\xd3\xdds\x95v\xe7\xc5A~c\xc1%\xa9]&\x14\xb9 \xa9\x8b\xf3$\xc3\x08\x0c\x1b\x06l#\xb0\x13\x046\xe4\x181\x90

尝试了各种转换各种decode 无效，希望各位大佬能指点迷津。

urllib不行后换了其它的三方库，requests和httplib2两个库均可，大家有类似情况可参考：

## Available

h = httplib2.Http('.cache')

resp, content = h.request(url)

# print(content.decode())

return content.decode()

## Available

resp = requests.get(url, headers=headers,
timeout=10,
verify=False)

contents = resp.content

# print(type(contents))

# print(contents)

完整代码：

import requests
import csv
import socket
import urllib.request as req
import urllib
from bs4 import BeautifulSoup
import gzip
import ssl
import httplib2

# 获取双色球往期数据
# @author puck
# @Date 2018-02-01
# https://datachart.500.com/ssq/history/history.shtml # https://datachart.500.com/ssq/history/newinc/history.php?limit=30&sort=0 
def get_content(url):
try:
context = ssl._create_unverified_context()
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
# requset = req.Request(url, headers=headers, method='GET')
# result = req.urlopen(requset, timeout=10, context=context).read() # 此方法获取的内容貌似16进制乱码
# rep.encoding = 'utf-8'
# return rep.text
# print(type(result))
# print(result.decode())

## Available
# h = httplib2.Http('.cache')
# resp, content = h.request(url)
# print(content.decode())
# return content.decode()

## Available
resp = requests.get(url, headers=headers, timeout=10, verify=False) # verify 参数必传，falst不校验SSL证书
contents = resp.content
# print(type(contents))
# print(contents)
if contents:
return contents.decode()
else:
print("can't get data from url:" + url)
except req.HTTPError as e:
print('HTTPError:', e)
except req.URLError as e:
# SSL证书验证失败错误
# URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:748)>
print('URLError:', e)
except socket.timeout as e:
print('socket.timeout:', e)
except BaseException as e:
print('BaseException:', e)

def get_data(html):
if html is None:
return
final = []
bs = BeautifulSoup(html, "html.parser")
print(bs)
datas = bs.find("tbody", {'id': 'tdata'})
trs = datas.find_all('tr')
for tr in trs:
temp = []
tds = tr.find_all('td')
temp.append(tds[0].string)
temp.append(tds[1].string)
temp.append(tds[2].string)
temp.append(tds[3].string)
temp.append(tds[4].string)
temp.append(tds[5].string)
temp.append(tds[6].string)
temp.append(tds[7].string)
final.append(temp)
print(final)
return final

def write_data(data, name):
with open(name, 'w', errors='ignore', newline='') as f:
csvFile = csv.writer(f)
csvFile.writerows(data)

if  __name__  == '__main__':
url = 'https://datachart.500.com/ssq/history/newinc/history.php?limit=30&sort=0'
html = get_content(url)
data = get_data(html)
write_data(data, 'TwoColorBallData30.csv')

爬取结果：

18016,01,11,12,18,25,27,16

18015,11,15,20,21,26,33,15

18014,09,12,20,24,28,31,07

18013,06,08,13,15,22,33,06

18012,11,12,13,19,26,28,12

18011,03,10,21,23,27,33,11

18010,01,08,17,20,21,22,03

18009,05,10,17,23,26,32,07

18008,05,09,10,12,17,19,13

18007,13,14,20,25,27,31,12

18006,02,07,08,09,17,29,11

18005,02,20,21,28,31,33,06

18004,14,18,19,26,30,31,11

18003,01,14,16,17,20,31,04

18002,07,18,24,29,31,33,16

18001,01,08,11,26,28,31,04

17154,05,09,13,15,18,26,05

17153,07,11,12,13,18,19,16

17152,06,10,23,25,26,29,05

17151,02,05,07,09,11,27,16

17150,06,14,19,20,21,23,08

17149,05,08,15,20,27,30,13

17148,04,07,11,14,29,32,12

17147,03,07,20,21,25,31,14

17146,01,19,25,26,27,33,10

17145,02,06,12,17,25,28,12

17144,03,14,16,20,31,32,09

17143,04,06,09,14,20,29,14

17142,08,13,14,18,23,33,06

17141,01,06,07,11,13,15,05

以上。