500彩票接口

双色球：出球顺序

http://datachart.500.com/ssq/history/newinc/outball.php

双色球：开奖信息

http://datachart.500.com/ssq/history/newinc/history.php

接口居然支持limit

http://datachart.500.com/ssq/history/newinc/history.php?limit=100000&sort=0

https://blog.csdn.net/weixin_36751895/article/details/78265985

Python双色球爬虫

import requests
from lxml import etree
import matplotlib.pyplot as plt
from pandas import Series

url = "http://datachart.500.com/ssq/history/newinc/history.php?start=00001&end=18154"
response = requests.get(url)  #获取响应文件
response = response.text  #将响应文件转换为文本
selector = etree.HTML(response)  #lxml.etree.HTML(r.text) 解析HTML，初始化生成一个XPath解析对象
reds = []
blues = []
for i in selector.xpath('//tr[@class="t_tr1"]'):  #选取给定属性具有给定值的所有元素
    #datetime = i.xpath('td/text()')[0]
    red = i.xpath('td/text()')[1:7]  #选取指定个数且具有指定元素的节点下的内容
    #print(type(red))  #<class 'list'>
    blue = i.xpath('td/text()')[7]  #选取指定个数且具有指定元素的节点下的内容
    for j in red:  #取出red列表里面的每一个数据并且append进resds列表
        reds.append(j)
    blues.append(blue)

#print(blues)
s_blues = Series(blues)
#print(s_blues)
s_blues = s_blues.value_counts()
s_reds = Series(reds)
#print(s_reds)
s_reds = s_reds.value_counts()


#print(s_blues)import requests
from lxml import etree
import matplotlib.pyplot as plt
from pandas import Series

url = "http://datachart.500.com/ssq/history/newinc/history.php?start=00001&end=18154"
response = requests.get(url)  #获取响应文件
response = response.text  #将响应文件转换为文本
selector = etree.HTML(response)  #lxml.etree.HTML(r.text) 解析HTML，初始化生成一个XPath解析对象
reds = []
blues = []
for i in selector.xpath('//tr[@class="t_tr1"]'):  #选取给定属性具有给定值的所有元素
    #datetime = i.xpath('td/text()')[0]
    red = i.xpath('td/text()')[1:7]  #选取指定个数且具有指定元素的节点下的内容
    #print(type(red))  #<class 'list'>
    blue = i.xpath('td/text()')[7]  #选取指定个数且具有指定元素的节点下的内容
    for j in red:  #取出red列表里面的每一个数据并且append进resds列表
        reds.append(j)
    blues.append(blue)

#print(blues)
s_blues = Series(blues)
#print(s_blues)
s_blues = s_blues.value_counts()
s_reds = Series(reds)
#print(s_reds)
s_reds = s_reds.value_counts()


#print(s_blues)
#print(s_reds)


def autolabel(rects):
    for rect in rects:
        height = rect.get_height()
        plt.text(rect.get_x(), 1.02*height, "%s" % height)


labels = s_blues.index.tolist()
sizes = s_blues.values.tolist()
#print(labels)
#print(sizes)
rect = plt.bar(range(len(sizes)), sizes, tick_label=labels)
autolabel(rect)
plt.show()

labels2 = s_reds.index.tolist()
sizes2 = s_reds.values.tolist()
rect2 = plt.bar(range(len(sizes2)), sizes2, tick_label=labels2)
autolabel(rect2)
plt.show()
#print(s_reds)


def autolabel(rects):
    for rect in rects:
        height = rect.get_height()
        plt.text(rect.get_x(), 1.02*height, "%s" % height)


labels = s_blues.index.tolist()
sizes = s_blues.values.tolist()
#print(labels)
#print(sizes)
rect = plt.bar(range(len(sizes)), sizes, tick_label=labels)
autolabel(rect)
plt.show()

labels2 = s_reds.index.tolist()
sizes2 = s_reds.values.tolist()
rect2 = plt.bar(range(len(sizes2)), sizes2, tick_label=labels2)
autolabel(rect2)
plt.show()

Python大乐透爬虫

import requests
from lxml import etree
import matplotlib.pyplot as plt
from pandas import Series

url = "http://datachart.500.com/dlt/history/newinc/history.php?start=00001&end=18154"
response = requests.get(url)
response = response.text
selector = etree.HTML(response)
reds = []
blues = []
for i in selector.xpath('//tr[@class="t_tr1"]')[1:]:
    #print(type(i))  #<class 'lxml.etree._Element'>
    #datetime = i.xpath('td/text()')[0]
    red = i.xpath('td/text()')[1:6]
    # print(type(red))
    blue = i.xpath('td/text()')[6:8]
    for j in red:
        reds.append(j)
    for k in blue:
        blues.append(k)


s_blues = Series(blues)
s_blues = s_blues.value_counts()
s_reds = Series(reds)
s_reds = s_reds.value_counts()


def autolabel(rects):
    for rect in rects:
        height = rect.get_height()
        plt.text(rect.get_x(), 1.02*height, "%s" % height)


# 蓝球统计表
labels = s_blues.index.tolist()
sizes = s_blues.values.tolist()
rect = plt.bar(range(len(sizes)), sizes, tick_label=labels)
autolabel(rect)
plt.show()


# 红球统计表
labels2 = s_reds.index.tolist()
sizes2 = s_reds.values.tolist()
rect2 = plt.bar(range(len(sizes2)), sizes2, tick_label=labels2)
autolabel(rect2)
plt.show()