zc3945 / caipanwenshu Goto Github PK

class DocSpider(scrapy.Spider):
name = 'doc'
allowed_domains = ['gov.cn']
start_urls = ['http://gov.cn/']

def start_requests(self):
    url = 'http://wenshu.court.gov.cn/list/list/?sorttype=1&conditions=searchWord+%E5%90%88%E5%90%8C+++%E5%85%B3%E9%94%AE%E8%AF%8D:%E5%90%88%E5%90%8C'
    yield scrapy.Request(url, callback=self.parse)

def parse(self, response):
    """
    根据日期查询分类数量
    :param response:
    :return:
    """
    cookie = response.headers['Set-Cookie'].split(';')[0][6:]
    vjkl5 = getvjkl5(cookie)
    for index in range(1, 2):
        end_day = (datetime.datetime.now() - datetime.timedelta(days=index)).date().__str__()
        start_day = (datetime.datetime.now() - datetime.timedelta(days=index+1)).date().__str__()
        Param = u'上传日期:{} TO {}'.format(start_day, end_day)
        data = {'Param': Param, 'vl5x': vjkl5}
        yield scrapy.FormRequest('http://wenshu.court.gov.cn/List/TreeContent', headers={'Cookie': cookie},
                                 callback=self.get_tree_list, formdata=data,
                                 meta={'cookie': cookie, 'vjkl5': vjkl5, 'Param': Param,
                                       'type_list': [u'法院地域', u'文书类型', u'法院层级',u'审判程序', u'裁判年份', u'一级案由']})

如上所示，在获取左侧tree结构时，有一个参数名字叫“上传日期”，对照裁判文书网抓包记录中，未发现有参数名字叫这个啊？求示意。

是不是网站又更新了反爬策略？
报错如下：
2018-12-26 17:13:54 [scrapy.utils.log] INFO: Scrapy 1.5.1 started (bot: wenshu) 2018-12-26 17:13:54 [scrapy.utils.log] INFO: Versions: lxml 4.2.5.0, libxml2 2.9.8, cssselect 1.0.3, parsel 1.5.1, w3lib 1.19.0, Twisted 18.9.0, Python 2.7.5 (default, Jul 13 2018, 13:06:57) - [GCC 4.8.5 20150623 (Red Hat 4.8.5-28)], pyOpenSSL 18.0.0 (OpenSSL 1.1.0f 25 May 2017), cryptography 2.1, Platform Linux-3.10.0-514.26.2.el7.x86_64-x86_64-with-centos-7.2.1511-Core 2018-12-26 17:13:54 [scrapy.crawler] INFO: Overridden settings: {'NEWSPIDER_MODULE': 'wenshu.spiders', 'ROBOTSTXT_OBEY': True, 'CONCURRENT_REQUESTS': 8, 'SPIDER_MODULES': ['wenshu.spiders'], 'BOT_NAME': 'wenshu', 'DOWNLOAD_DELAY': 3} 2018-12-26 17:13:54 [scrapy.middleware] INFO: Enabled extensions: ['scrapy.extensions.memusage.MemoryUsage', 'scrapy.extensions.logstats.LogStats', 'scrapy.extensions.telnet.TelnetConsole', 'scrapy.extensions.corestats.CoreStats'] 2018-12-26 17:13:54 [scrapy.middleware] INFO: Enabled downloader middlewares: ['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware', 'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware', 'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware', 'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware', 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware', 'scrapy.downloadermiddlewares.retry.RetryMiddleware', 'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware', 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware', 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware', 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware', 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware', 'scrapy.downloadermiddlewares.stats.DownloaderStats'] 2018-12-26 17:13:54 [scrapy.middleware] INFO: Enabled spider middlewares: ['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware', 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware', 'scrapy.spidermiddlewares.referer.RefererMiddleware', 'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware', 'scrapy.spidermiddlewares.depth.DepthMiddleware'] 2018-12-26 17:13:54 [scrapy.middleware] INFO: Enabled item pipelines: ['wenshu.pipelines.WenshuPipeline'] 2018-12-26 17:13:54 [scrapy.core.engine] INFO: Spider opened 2018-12-26 17:13:54 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min) 2018-12-26 17:13:54 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023 2018-12-26 17:13:58 [scrapy.core.engine] DEBUG: Crawled (404) <GET http://wenshu.court.gov.cn/robots.txt> (referer: None) 2018-12-26 17:14:02 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://wenshu.court.gov.cn/List/List?sorttype=1&conditions=searchWord+1+AJLX++%E6%A1%88%E4%BB%B6%E7%B1%BB%E5%9E%8B:%E5%88%91%E4%BA%8B%E6%A1%88%E4%BB%B6> (referer: None) 2018-12-26 17:14:08 [scrapy.core.engine] DEBUG: Crawled (200) <POST http://wenshu.court.gov.cn/List/TreeContent> (referer: http://wenshu.court.gov.cn/List/List?sorttype=1&conditions=searchWord+1+AJLX++%E6%A1%88%E4%BB%B6%E7%B1%BB%E5%9E%8B:%E5%88%91%E4%BA%8B%E6%A1%88%E4%BB%B6) 2018-12-26 17:14:08 [scrapy.core.engine] DEBUG: Crawled (200) <POST http://wenshu.court.gov.cn/List/TreeContent> (referer: http://wenshu.court.gov.cn/List/TreeContent) 2018-12-26 17:14:15 [scrapy.core.engine] DEBUG: Crawled (200) <POST http://wenshu.court.gov.cn/List/TreeContent> (referer: http://wenshu.court.gov.cn/List/TreeContent) 2018-12-26 17:14:17 [scrapy.core.engine] DEBUG: Crawled (200) <POST http://wenshu.court.gov.cn/List/TreeContent> (referer: http://wenshu.court.gov.cn/List/TreeContent) 2018-12-26 17:14:20 [scrapy.core.engine] DEBUG: Crawled (200) <POST http://wenshu.court.gov.cn/List/ListContent> (referer: http://wenshu.court.gov.cn/List/TreeContent) 2018-12-26 17:14:20 [scrapy.core.scraper] ERROR: Spider error processing <POST http://wenshu.court.gov.cn/List/ListContent> (referer: http://wenshu.court.gov.cn/List/TreeContent) Traceback (most recent call last): File "/usr/lib64/python2.7/site-packages/scrapy/utils/defer.py", line 102, in iter_errback yield next(it) File "/usr/lib64/python2.7/site-packages/scrapy/spidermiddlewares/offsite.py", line 30, in process_spider_output for x in result: File "/usr/lib64/python2.7/site-packages/scrapy/spidermiddlewares/referer.py", line 339, in <genexpr> return (_set_referer(r) for r in result or ()) File "/usr/lib64/python2.7/site-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr> return (r for r in result or () if _filter(r)) File "/usr/lib64/python2.7/site-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr> return (r for r in result or () if _filter(r)) File "/www/wenshu/wenshu/spiders/doc.py", line 95, in get_doc_list key = getkey(format_key_str).encode('utf-8') File "/www/wenshu/wenshu/utils/docid_v27.py", line 105, in getkey c = execjs.compile(js_str) File "/usr/lib/python2.7/site-packages/execjs/__init__.py", line 61, in compile return get().compile(source, cwd) File "/usr/lib/python2.7/site-packages/execjs/_runtimes.py", line 21, in get return get_from_environment() or _find_available_runtime() File "/usr/lib/python2.7/site-packages/execjs/_runtimes.py", line 49, in _find_available_runtime raise exceptions.RuntimeUnavailableError("Could not find an available JavaScript runtime.") RuntimeUnavailableError: Could not find an available JavaScript runtime.

我clone 你得代码 直接执行docid文件提示下面错误
我使用得是python3

比如限定时间2020年，我看了chrome devtool里面的请求是设置queryCondition，但是我在demo.py里加了不起作用，直接失败了。谢谢

有时执行正常，有时执行错误。报错如下

2018-12-18 17:46:21 [scrapy.core.scraper] ERROR: Spider error processing <GET http://wenshu.court.gov.cn/list/list/?sorttype=1> (referer: None)
Traceback (most recent call last):
File "c:\users\qiqing\appdata\local\programs\python\python37\lib\site-packages\scrapy\utils\defer.py", line 102, in iter_errback
yield next(it)
File "c:\users\qiqing\appdata\local\programs\python\python37\lib\site-packages\scrapy\spidermiddlewares\offsite.py", line 30, in process_spider_output
for x in result:
File "c:\users\qiqing\appdata\local\programs\python\python37\lib\site-packages\scrapy\spidermiddlewares\referer.py", line 339, in
return (_set_referer(r) for r in result or ())
File "c:\users\qiqing\appdata\local\programs\python\python37\lib\site-packages\scrapy\spidermiddlewares\urllength.py", line 37, in
return (r for r in result or () if _filter(r))
File "c:\users\qiqing\appdata\local\programs\python\python37\lib\site-packages\scrapy\spidermiddlewares\depth.py", line 58, in
return (r for r in result or () if _filter(r))
File "D:\Work\JingShOnline\Spider\wenshu\wenshu\spiders\wenshu.py", line 20, in parse
vjkl5 = getvjkl5(cookie)
File "D:\Work\JingShOnline\Spider\wenshu\wenshu\utils\vl5x.py", line 1806, in getvjkl5
vjkl5 = arrFunfunIndex
File "D:\Work\JingShOnline\Spider\wenshu\wenshu\utils\vl5x.py", line 755, in makeKey_150
return md5(makeKey_14(str1) + makeKey_19(str1))[1: 1 + 24]
File "D:\Work\JingShOnline\Spider\wenshu\wenshu\utils\vl5x.py", line 175, in makeKey_14
b = base64.b64encode(s[1:] + s[5:] + s[1:4])
File "c:\users\qiqing\appdata\local\programs\python\python37\lib\base64.py", line 58, in b64encode
encoded = binascii.b2a_base64(s, newline=False)
TypeError: a bytes-like object is required, not 'str'

AssertionError: 文书网异常，80s获取失败

多了MmEwMD 参数