使用scrapy搜寻动态网页以获取数据

在此示例中，JavaScript仅允许在网页上发送，接收和显示内容，而无需为每个请求实际重新加载网页。因此，您无需解析javascript，只需要查找请求的信息，然后模仿该请求，然后解析响应即可。为此，您可以在Firefox中使用Firebug，或在Chrome中使用开发人员工具（在Windows中为ctrl + shift + J，在Mac中为cmd + opt + J）。在Chrome浏览器中，只需单击“网络”标签，然后在网站上单击即可看到请求和响应。

在此特定示例中，当您想要获取“ 2008-09”的克里夫兰队的统计信息时，javascript将发送多个请求。您可能会对感兴趣的节目单请求是这样的：http : //stats.nba.com/stats/teamdashlineups? PlusMinus=N&pageNo=1&GroupQuantity=5&TeamID=1610612739&GameID=&Location=&SeasonType=Regular+Season&Season=2008- 09＆PaceAdjust = N＆DateFrom =＆sortOrder = DES＆VsConference =＆OpponentTeamID = 0＆DateTo =＆GameSegment =＆LastNGames = 0＆VsDivision =＆LeagueID = 00＆Outcome =＆GameScope =＆MeasureType = Base＆PerMode = Per48＆sortField = MIN＆SeasonSegth = &&

这是一个易碎的基础蜘蛛的例子。您只需要定义LineupItem，然后可以使用来执行它scrapy crawl stats -o output.json。

import json
from scrapy.spider import Spider
from scrapy.http import Request
from nba.items import LineupItem
from urllib import urlencode


class StatsSpider(Spider):
    name = "stats"
    allowed_domains = ["stats.nba.com"]
    start_urls = (
        'http://stats.nba.com/',
        )

    def parse(self, response):
        return self.get_lineup('1610612739','2008-09')

    def get_lineup(self, team_id, season):
        params = {
            'Season':         season,
            'SeasonType':     'Regular Season',
            'LeagueID':       '00',
            'TeamID':         team_id,
            'MeasureType':    'Base',
            'PerMode':        'Per48',
            'PlusMinus':      'N',
            'PaceAdjust':     'N',
            'Rank':           'N',
            'Outcome':        '',
            'Location':       '',
            'Month':          '0',
            'SeasonSegment':  '',
            'DateFrom':       '',
            'DateTo':         '',
            'OpponentTeamID': '0',
            'VsConference':   '',
            'VsDivision':     '',
            'GameSegment':    '',
            'Period':         '0',
            'LastNGames':     '0',
            'GroupQuantity':  '5',
            'GameScope':      '',
            'GameID':         '',
            'pageNo':         '1',
            'rowsPerPage':    '100',
            'sortField':      'MIN',
            'sortOrder':      'DES'
        }
        return Request(
            url="http://stats.nba.com/stats/teamdashlineups?" + urlencode(params),
            dont_filter=True,
            callback=self.parse_lineup
        )

    def parse_lineup(self,response):
        data = json.loads(response.body)
        for lineup in data['resultSets'][1]['rowSet']:
            item = LineupItem()
            item['group_set'] = lineup[0]
            item['group_id'] = lineup[1]
            item['group_name'] = lineup[2]
            item['gp'] = lineup[3]
            item['w'] = lineup[4]
            item['l'] = lineup[5]
            item['w_pct'] = lineup[6]
            item['min'] = lineup[7]
            item['fgm'] = lineup[8]
            item['fga'] = lineup[9]
            item['fg_pct'] = lineup[10]
            item['fg3m'] = lineup[11]
            item['fg3a'] = lineup[12]
            item['fg3_pct'] = lineup[13]
            item['ftm'] = lineup[14]
            item['fta'] = lineup[15]
            item['ft_pct'] = lineup[16]
            item['oreb'] = lineup[17]
            item['dreb'] = lineup[18]
            item['reb'] = lineup[19]
            item['ast'] = lineup[20]
            item['tov'] = lineup[21]
            item['stl'] = lineup[22]
            item['blk'] = lineup[23]
            item['blka'] = lineup[24]
            item['pf'] = lineup[25]
            item['pfd'] = lineup[26]
            item['pts'] = lineup[27]
            item['plus_minus'] = lineup[28]
            yield item

这将导致像这样的json记录：

{"gp": 30, "fg_pct": 0.491, "group_name": "Ilgauskas,Zydrunas - James,LeBron - Wallace,Ben - West,Delonte - Williams,Mo", "group_set": "Lineups", "w_pct": 0.833, "pts": 103.0, "min": 484.9866666666667, "tov": 13.3, "fta": 21.6, "pf": 16.0, "blk": 7.7, "reb": 44.2, "blka": 3.0, "ftm": 16.6, "ft_pct": 0.771, "fg3a": 18.7, "pfd": 17.2, "ast": 23.3, "fg3m": 7.4, "fgm": 39.5, "fg3_pct": 0.397, "dreb": 32.0, "fga": 80.4, "plus_minus": 18.4, "stl": 8.3, "l": 5, "oreb": 12.3, "w": 25, "group_id": "980 - 2544 - 1112 - 2753 - 2590"}