feats

crawl/comm/football.py

     whole = None,
 
     # 状态
-    status = None
+    status = None,
+
+    # 玩法结果
+    playRes = None,
   ):
     self.matchTime = matchTime
     self.matchWeek = matchWeek
     self.half = half
     self.whole = whole
     self.status = status
+    self.playRes = playRes
 
   def toString(self):
     return ';'.join((
-      self.matchTime if self.matchTime is not None else '',
-      self.matchWeek if self.matchWeek is not None else '',
-      self.league if self.league is not None else '',
-      self.homeTeam if self.homeTeam is not None else '',
-      self.awayTeam if self.awayTeam is not None else '',
-      self.single if self.single is not None else '',
-      self.half if self.half is not None else '',
-      self.whole if self.whole is not None else '',
-      self.status if self.status is not None else ''
+      self.matchTime,
+      self.matchWeek,
+      self.league,
+      self.homeTeam,
+      self.awayTeam,
+      self.single,
+      self.half,
+      self.whole,
+      self.status,
+      self.playRes,
     ))
 
   def persist(self):

crawl/spiders/basketball_result.py

         ''
       )
 
-      matchLink = getNoneStr(tdNodeList[12].css('a').attrib.get('href'))
-      matchId = re.sub(r'^.*pool_result.php\?id=', '', matchLink)
+      matchLink = getNoneStr(tdNodeList[3].css('a').attrib.get('href'))
+      matchId = re.sub(r'^.*bk_match_info.php\?m=', '', matchLink)
 
       # 加入到临时字典里
       self._matchesMap[matchId] = bstResult
 
       if status == '已完成':
-        yield scrapy.Request('https:' + matchLink, self.parsePrice, 'GET')
+        link = tdNodeList[12].css('a').attrib.get('href')
+        yield scrapy.Request('https:' + link, self.parsePrice, 'GET')
       else:
         logging.info("采集到数据 --> %s" % bstResult.toString())
         bstResult.persist()
 
     tableList = response.css('.kj-table')
     if tableList is None or len(tableList) < 4:
-      logging.error("抓取赔率结果失败")
+      logging.error("抓取玩法结果失败")
       return
 
     playRes = []

crawl/spiders/football_result.py

 import re
 import logging
 from crawl.comm.football import FTResult
+from crawl.spiders.util import getNoneStr
 
 class FootballSpider(scrapy.Spider):
   name = "football-result"
 
+  # 所有比赛
+  _matchesMap = {}
+
   def start_requests(self):
     url = 'https://info.sporttery.cn/football/match_result.php'
     yield scrapy.Request(url, self.parseResult, 'GET')
       if tdNodeList is None or len(tdNodeList) < 10:
         continue
 
-      matchTime = tdNodeList[0].css('::text').get()
-      matchWeek = tdNodeList[1].css('::text').get()
-      league = tdNodeList[2].css('::text').get()
-      leagueFullName = tdNodeList[2].attrib.get('title')  # 联赛全称
-      leagueName = '|'.join((league if league is not None else '', leagueFullName if leagueFullName is not None else ''))
+      matchTime = getNoneStr(tdNodeList[0].css('::text').get())
+      matchWeek = getNoneStr(tdNodeList[1].css('::text').get())
+      league = getNoneStr(tdNodeList[2].css('::text').get())
+      leagueFullName = getNoneStr(tdNodeList[2].attrib.get('title'))  # 联赛全称
+      leagueName = '|'.join((league, leagueFullName))
       homeTeam = self.trimBrackets(tdNodeList[3].css('.zhu::text').get()) # 主队
       awayTeam = self.trimBrackets(tdNodeList[3].css('.ke::text').get()) # 客队
-      half = tdNodeList[4].css('span::text').get()
-      whole = tdNodeList[5].css('span::text').get()
-      status = tdNodeList[9].css('::text').get()
+      half = getNoneStr(tdNodeList[4].css('span::text').get())
+      whole = getNoneStr(tdNodeList[5].css('span::text').get())
+      status = getNoneStr(tdNodeList[9].css('::text').get())
 
       ftResult = FTResult(
         matchTime,
         '', # 不需要单固
         half,
         whole,
-        status
+        status,
+        ''
       )
-      
-      logging.info("采集到数据 --> %s" % ftResult.toString())
 
-      ftResult.persist()
+      matchLink = getNoneStr(tdNodeList[3].css('a').attrib.get('href'))
+      matchId = re.sub(r'^.*fb_match_info.php\?m=', '', matchLink)
+
+      # 加入到临时字典里
+      self._matchesMap[matchId] = ftResult
+
+
+      if status == '已完成':
+        link = "https://i.sporttery.cn/api/fb_match_info/get_pool_rs?mid=" + matchId
+        yield scrapy.Request(link, self.parsePrice, 'GET')
+      else:
+        logging.info("采集到数据 --> %s" % ftResult.toString())
+        ftResult.persist()
 
 
     # 是否存在下一页
     if str is None: return ''
 
     return re.sub(r'\(.*\)', '', str)
+
+  def parsePrice(self, response):
+    logging.info("采集数据源 ---> %s" % response.url)
+    
+    data = response.json()
+    res = data.get('result').get('pool_rs')
+
+    playRes = []
+
+    # 胜平负
+    playRes.append(res['had']['prs_name'])
+    # 让球胜平负
+    playRes.append(res['hhad']['prs_name'])
+    # 比分
+    playRes.append(res['crs']['prs_name'])
+    # 总进球
+    playRes.append(res['ttg']['prs_name'])
+    # 半全场
+    playRes.append(res['hafu']['prs_name'])
+
+    matchId = re.sub(r'^.*get_pool_rs\?mid=', '', response.url)
+    ftResult = self._matchesMap[matchId]
+    ftResult.playRes = '|'.join(playRes)
+
+    #
+    logging.info("采集到数据 --> %s" % ftResult.toString())
+
+    # 入库
+    ftResult.persist()