张延森 4 years ago
parent
commit
35e3c7c5f2
1 changed files with 3 additions and 0 deletions
  1. 3
    0
      crawl/spiders/basketball.py

+ 3
- 0
crawl/spiders/basketball.py View File

29
       league = getNoneStr(tdNodeList[1].css('::text').get())  # 联赛简称
29
       league = getNoneStr(tdNodeList[1].css('::text').get())  # 联赛简称
30
       leagueFullName = getNoneStr(tdNodeList[1].attrib.get('title'))  # 联赛全称
30
       leagueFullName = getNoneStr(tdNodeList[1].attrib.get('title'))  # 联赛全称
31
       leagueName = '|'.join((league, leagueFullName))
31
       leagueName = '|'.join((league, leagueFullName))
32
+
33
+      # 抓取页面上显示正确. 但是样式 zhu ke 的标记是反的
34
+      # 暂时就不处理了。后续使用 sql 纠正过来
32
       homeTeam = getNoneStr(tdNodeList[2].css('.zhu::text').get())  # 主队
35
       homeTeam = getNoneStr(tdNodeList[2].css('.zhu::text').get())  # 主队
33
       awayTeam = getNoneStr(tdNodeList[2].css('.ke::text').get())  # 客队
36
       awayTeam = getNoneStr(tdNodeList[2].css('.ke::text').get())  # 客队
34
       matchTime = getNoneStr(tdNodeList[3].css('::text').get())  # 比赛时间
37
       matchTime = getNoneStr(tdNodeList[3].css('::text').get())  # 比赛时间