张延森 4 年前
父节点
当前提交
618d9a8739

二进制
crawl/__pycache__/__init__.cpython-38.pyc 查看文件


二进制
crawl/__pycache__/settings.cpython-38.pyc 查看文件


二进制
crawl/comm/__pycache__/__init__.cpython-38.pyc 查看文件


二进制
crawl/comm/__pycache__/basketball.cpython-38.pyc 查看文件


二进制
crawl/comm/__pycache__/football.cpython-38.pyc 查看文件


二进制
crawl/comm/__pycache__/lottery.cpython-38.pyc 查看文件


二进制
crawl/comm/__pycache__/mydb.cpython-38.pyc 查看文件


+ 1
- 1
crawl/run.py 查看文件

7
 # 添加环境变量
7
 # 添加环境变量
8
 sys.path.append(dirpath)
8
 sys.path.append(dirpath)
9
 # 启动爬虫,第三个参数为爬虫name
9
 # 启动爬虫,第三个参数为爬虫name
10
-execute(['scrapy','crawl','football-result'])
10
+execute(['scrapy','crawl','basketball-result'])

二进制
crawl/spiders/__pycache__/__init__.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/basketball.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/basketball_match.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/basketball_price.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/basketball_result.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/football.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/football_match.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/football_price.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/football_result.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/lottery.cpython-38.pyc 查看文件


二进制
crawl/spiders/__pycache__/util.cpython-38.pyc 查看文件


+ 9
- 6
crawl/spiders/basketball_result.py 查看文件

30
       league = getNoneStr(tdNodeList[2].css('::text').get())
30
       league = getNoneStr(tdNodeList[2].css('::text').get())
31
       leagueFullName = getNoneStr(tdNodeList[2].attrib.get('title'))  # 联赛全称
31
       leagueFullName = getNoneStr(tdNodeList[2].attrib.get('title'))  # 联赛全称
32
       leagueName = '|'.join((league, leagueFullName))
32
       leagueName = '|'.join((league, leagueFullName))
33
-      homeTeam = self.trimBrackets(getNoneStr(tdNodeList[3].css('.zhu::text').get()))  # 主队
34
-      awayTeam = self.trimBrackets(getNoneStr(tdNodeList[3].css('.ke::text').get()))  # 客队
33
+      homeTeam = self.trimBrackets(getNoneStr(tdNodeList[3].css('.zhu1::text').get()))  # 主队
34
+      awayTeam = self.trimBrackets(getNoneStr(tdNodeList[3].css('.ke1::text').get()))  # 客队
35
 
35
 
36
       half = ''
36
       half = ''
37
       halfSpan = tdNodeList[4].css('span')
37
       halfSpan = tdNodeList[4].css('span')
38
       if halfSpan is not None and len(halfSpan) > 0:
38
       if halfSpan is not None and len(halfSpan) > 0:
39
-        part1 = getNoneStr(tdNodeList[4].css("span::text")[0].get())
40
-        part2 = getNoneStr(tdNodeList[4].css("span::text")[1].get())
41
-        part3 = getNoneStr(tdNodeList[5].css("span::text")[0].get())
42
-        part4 = getNoneStr(tdNodeList[5].css("span::text")[1].get())
39
+        part1 = getNoneStr(tdNodeList[4].css("span")[0].css("::text").get())
40
+        part2 = getNoneStr(tdNodeList[4].css("span")[1].css("::text").get())
41
+        part3 = getNoneStr(tdNodeList[5].css("span")[0].css("::text").get())
42
+        part4 = getNoneStr(tdNodeList[5].css("span")[1].css("::text").get())
43
         part5 = getNoneStr(tdNodeList[6].css('::text').get())
43
         part5 = getNoneStr(tdNodeList[6].css('::text').get())
44
         half = '|'.join((part1, part2, part3, part4, part5))
44
         half = '|'.join((part1, part2, part3, part4, part5))
45
 
45
 
49
       if whole == '无效场次':
49
       if whole == '无效场次':
50
         status = '无效场次'
50
         status = '无效场次'
51
 
51
 
52
+      if status == '进行中':
53
+        continue
54
+
52
       bstResult = BSTResult(
55
       bstResult = BSTResult(
53
         matchTime,
56
         matchTime,
54
         matchWeek,
57
         matchWeek,

+ 3
- 0
crawl/spiders/football_result.py 查看文件

35
       whole = getNoneStr(tdNodeList[5].css('span::text').get())
35
       whole = getNoneStr(tdNodeList[5].css('span::text').get())
36
       status = getNoneStr(tdNodeList[9].css('::text').get())
36
       status = getNoneStr(tdNodeList[9].css('::text').get())
37
 
37
 
38
+      if status == '进行中':
39
+        continue
40
+
38
       ftResult = FTResult(
41
       ftResult = FTResult(
39
         matchTime,
42
         matchTime,
40
         matchWeek,
43
         matchWeek,