如何使用这个python程序

Question

代码如下

import json
import requests
from scrapy.crawler import logger


def get_rbballData(self, dayStart, dayEnd):
    """
    爬虫主程序
    """
    pageNo = 1
    session = self._get_session()

    while pageNo <= self.pageNum:
      # 循环抓取数据
      url = self._get_url(dayStart, dayEnd, pageNo)
      res_text = self._send_request(session, url)
      if res_text != None:
        ret = self._parseText_toData(res_text)

      pageNo = pageNo + 1

    count = self._save_rbballData()
    return count

def _get_url(self, dayStart, dayEnd, pageNo):
    """
    构造抓取的url
    """
    url = "http://www.cwl.gov.cn/cwl_admin/kjxx/findDrawNotice?name=ssq&issueCount=&issueStart=&issueEnd=&dayStart={}&dayEnd={}&pageNo={}"
    url = url.format(dayStart,dayEnd,pageNo)
    return url


def _get_session(self):
    """
    构造session
    """
    headers = {"Accept":"application/json, text/javascript, */*; q=0.01",
      "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36",
      "X-Requested-With":"XMLHttpRequest",
      "Accept-Encoding":"gzip, deflate",
      "Referer": "http://www.cwl.gov.cn/kjxx/ssq/kjgg/",
      "Accept-Language":"zh-CN,zh;q=0.9"}
    session = requests.Session()
    session.headers.update(headers)
    return session


def _send_request(self, session, url):
    """
    发送请求，并返回响应文本，
    return:请求成功返回文本，请求失败，返回None
    """
    res = session.get(url)
    if res.status_code != 200:
      res = None
      logger.info("请求url失败，url=[{}]".format(url))
    return res.text


def _parseText_toData(self, text):
    """
    获取一页双色球开奖结果，
    return:获取成功返回，未成功返回-1
    """
    try:
      text = json.loads(text)
      if text["state"] != 0:
        # 查询失败
        logger.info("查询返回失败，返回结果：[{}]".format(text))
        text = None
        return -1
    except Exception as e:
      logger.info("文本转换json失败，文本：【{}】".format(text))
      logger.info("异常信息：{}".format(str(e)))
      text = None
      return  -1
    #text["result"]本身是个dict,需将其逐个写入rbballData
    for t in text["result"]:
      self.rbballData.append(t)

    self.pageNum = text["pageCount"]
    return 0


def _save_rbballData(self):
    """
    将抓取到的数据保存到rbball_data.txt文件中
    reture: 返回双色球总期数
    """
    self.rbballData.reverse()
    print(self.rbballData[0]["code"])
    count = len(self.rbballData)
    if count > 0:
      with open("rbball_data.txt", 'w', encoding="utf-8") as f:
        f.write(str(self.rbballData))
    else:
      logger.info("未获取到双色球数据！！！")
    return count

我想使用这个代码

我写了个这个

if __name__=='__main__':
    get_rbballData(self, "2021-01-01", "2021-01-31")

但是报错

Answer 1

希望可以帮上你,对你有启发

from selenium import webdriver
from lxml import etree
import numpy as np


def arr_size(arr, size):
    s = []
    for i in range(0, int(len(arr)) + 1, size):
        c = arr[i:i + size]
        s.append(c)
    newlist = [x for x in s if x]
    return newlist


browser = webdriver.Chrome()  # 这里改成了有界面模式，方便调试代码
url = 'http://www.cwl.gov.cn/ygkj/wqkjgg/'
browser.get(url)
data = browser.page_source
browser.quit()
html = etree.HTML(data, parser=etree.HTMLParser(encoding='utf-8'))
qishu = html.xpath('/html/body/div[2]/div/div/div[2]/div/div/div[2]/table/tbody/tr/td[1]/text()')
code = html.xpath('/html/body/div[2]/div/div/div[2]/div/div/div[2]/table/tbody/tr/td[3]/div/div/text()')
code = [' '.join(i) for i in arr_size(code, 7)]
result = dict(zip(qishu, code))
for key, value in result.items():
    print("期数:{},中奖号码:{}".format(key, value))