scrapy 蜘蛛中的类型错误
TypeError in scrapy spider
注:
我正在抓取的页面直到我现在所在的位置才使用 javascript。我也试过使用 scrapy_splash 但得到了同样的错误！
我依靠 this 课程来启动蜘蛛。
问题：
scrapy spider 报错：
raise TypeError('to_bytes must receive a str or bytes '
TypeError: to_bytes must receive a str or bytes object, got Selector
我想要的：
作为输出的字符串，其中包括“一些记录”。
我尝试了什么？
and 等其他问题。他们没有解决我面临的问题。
我的代码：
import scrapy
from scrapy import FormRequest
class abcSpider(scrapy.Spider):
name = 'abc'
allowed_domains = ['citizen.mahapolice.gov.in']
def start_requests(self):
yield scrapy.Request(
url='http://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
headers={
'Referer': 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx'
},
callback=self.parse
)
def parse(self, response):
yield FormRequest.from_response(
response,
formid='form1',
formdata={
'__EVENTTARGET': response.xpath("//input[@name='__EVENTTARGET']/@value"),
'__EVENTARGUMENT': response.xpath("//*[@id='__EVENTARGUMENT']/@value"),
'__LASTFOCUS': response.xpath("//*[@id='__LASTFOCUS']/@value"),
'__VIEWSTATE':response.xpath("//*[@id='__VIEWSTATE']/@value"),
'__VIEWSTATEGENERATOR': "6F2EA376",
'__PREVIOUSPAGE': response.xpath("//*[@id='__PREVIOUSPAGE']/@value"),
'__EVENTVALIDATION': response.xpath("//*[@id='__EVENTVALIDATION']/@value"),
'ctl00$hdnSessionIdleTime': response.xpath("//*[@id='hdnSessionIdleTime']/@value"),
'ctl00$hdnUserUniqueId': response.xpath("//*[@id='hdnUserUniqueId']/@value"),
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationFrom_ClientState': response.xpath(
"//*[@id='ContentPlaceHolder1_meeDateOfRegistrationFrom_ClientState']/@value"),
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationFrom': "01/07/2020",
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationTo_ClientState':
response.xpath(
"//*[@id='ContentPlaceHolder1_meeDateOfRegistrationTo_ClientState']/@value"),
'ctl00$ContentPlaceHolder1_txtDateOfRegistrationTo': "03/07/2020",
'ctl00$ContentPlaceHolder1$ddlDistrict': "19409",
'ctl00$ContentPlaceHolder1$ddlPoliceStation': "",
'ctl00$ContentPlaceHolder1$txtFirno': "",
'ctl00$ContentPlaceHolder1$btnSearch': "Search",
'ctl00$ContentPlaceHolder1$ucRecordView$ddlPageSize': "0",
'ctl00$ContentPlaceHolder1$ucGridRecordView$txtPageNumber': ""
},
callback=(self.after_login),
)
def after_login(self, response):
police_stations = response.xpath(
'//*[@id="ContentPlaceHolder1_lbltotalrecord"]/text()').get()
print(police_stations)
终端输出：
2020-07-15 15:11:37 [scrapy.utils.log] INFO: Scrapy 2.2.0 started (bot: xyz)
2020-07-15 15:11:37 [scrapy.utils.log] INFO: Versions: lxml 4.5.0.0, libxml2 2.9.10, cssselect 1.1.0, parsel 1.6.0, w3lib 1.22.0, Twisted 20.3.0, Python 3.8.2 (default, Apr 27 2020, 15:53:34) - [GCC 9.3.0], pyOpenSSL 19.1.0 (OpenSSL 1.1.1f 31 Mar 2020), cryptography 2.8, Platform Linux-5.4.0-40-generic-x86_64-with-glibc2.29
2020-07-15 15:11:37 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.epollreactor.EPollReactor
2020-07-15 15:11:37 [scrapy.crawler] INFO: Overridden settings:
{'BOT_NAME': 'xyz',
'NEWSPIDER_MODULE': 'xyz.spiders',
'SPIDER_MODULES': ['xyz.spiders']}
2020-07-15 15:11:38 [scrapy.extensions.telnet] INFO: Telnet Password: db3dd9550774d0ab
2020-07-15 15:11:38 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.memusage.MemoryUsage',
'scrapy.extensions.logstats.LogStats']
2020-07-15 15:11:39 [scrapy.middleware] INFO: Enabled downloader middlewares:
['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']
2020-07-15 15:11:39 [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']
2020-07-15 15:11:39 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2020-07-15 15:11:39 [scrapy.core.engine] INFO: Spider opened
2020-07-15 15:11:39 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2020-07-15 15:11:39 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2020-07-15 15:11:40 [scrapy.downloadermiddlewares.redirect] DEBUG: Redirecting (302) to <GET https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx> from <GET http://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx>
2020-07-15 15:11:40 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx> (referer: https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx)
2020-07-15 15:11:40 [scrapy.core.scraper] ERROR: Spider error processing <GET https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx> (referer: https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx)
Traceback (most recent call last):
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/defer.py", line 120, in iter_errback
yield next(it)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/python.py", line 346, in __next__
return next(self.data)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/python.py", line 346, in __next__
return next(self.data)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output
for x in result:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/referer.py", line 340, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr>
return (r for r in result or () if _filter(r))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr>
return (r for r in result or () if _filter(r))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/Documents/delet/xyz/xyz/spiders/abc.py", line 20, in parse
yield FormRequest.from_response(
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 58, in from_response
return cls(url=url, method=method, formdata=formdata, **kwargs)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 31, in __init__
querystr = _urlencode(items, self.encoding)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 71, in _urlencode
values = [(to_bytes(k, enc), to_bytes(v, enc))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 71, in <listcomp>
values = [(to_bytes(k, enc), to_bytes(v, enc))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/python.py", line 104, in to_bytes
raise TypeError('to_bytes must receive a str or bytes '
TypeError: to_bytes must receive a str or bytes object, got Selector
2020-07-15 15:11:40 [scrapy.core.engine] INFO: Closing spider (finished)
2020-07-15 15:11:40 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 648,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 8150,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/302': 1,
'elapsed_time_seconds': 1.116569,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2020, 7, 15, 9, 41, 40, 607840),
'log_count/DEBUG': 2,
'log_count/ERROR': 1,
'log_count/INFO': 10,
'memusage/max': 52281344,
'memusage/startup': 52281344,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'spider_exceptions/TypeError': 1,
'start_time': datetime.datetime(2020, 7, 15, 9, 41, 39, 491271)}
2020-07-15 15:11:40 [scrapy.core.engine] INFO: Spider closed (finished)
你有问题，我在 previous question 的评论中提到过。
当您在 formdata={...}
中获取值 response.xpath(...).get() 时，您必须使用 .get()
顺便说一句：
你的字段名还是有误
'ContentPlaceHolder1_txtDateOfRegistrationTo': "03/07/2020",
必须
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationTo': "03/07/2020",
并且您必须在开始 url 时使用 https:// 而不是 http://。
url = 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
如果你使用 http:// 那么它会重定向到主页
https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx
然后您将表单发送到 index.aspx 而不是 PublishedFIRs.aspx
可以放在一个文件中的最少工作代码 运行 python script.py 而不会产生问题
它没有以前的错误，它发送到更正 url 但它仍然有值 __VIEWSTATE 和 __EVENTVALIDATION 的问题。如果我从网络浏览器复制所有值然后它工作但如果我使用来自 scrapy 的值然后页面生成错误 500。可能页面使用 JavaScript 生成这些值。
#!/usr/bin/env python3
import scrapy
from scrapy import FormRequest
class abcSpider(scrapy.Spider):
name = 'abc'
allowed_domains = ['citizen.mahapolice.gov.in']
def start_requests(self):
yield scrapy.Request(
url='https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
headers={
'USER_AGENT': 'Mozilla/5.0',
'Referer': 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx'
},
callback=self.parse
)
def parse(self, response):
yield FormRequest.from_response(
response,
formid='form1',
formdata={
'__EVENTTARGET': response.xpath("//input[@name='__EVENTTARGET']/@value").get(),
'__EVENTARGUMENT': response.xpath("//*[@id='__EVENTARGUMENT']/@value").get(),
'__LASTFOCUS': response.xpath("//*[@id='__LASTFOCUS']/@value").get(),
'__VIEWSTATE':response.xpath("//*[@id='__VIEWSTATE']/@value").get(),
'__VIEWSTATEGENERATOR': "6F2EA376",
'__PREVIOUSPAGE': response.xpath("//*[@id='__PREVIOUSPAGE']/@value").get(),
'__EVENTVALIDATION': response.xpath("//*[@id='__EVENTVALIDATION']/@value").get(),
'ctl00$hdnSessionIdleTime': response.xpath("//*[@id='hdnSessionIdleTime']/@value").get(),
'ctl00$hdnUserUniqueId': response.xpath("//*[@id='hdnUserUniqueId']/@value").get(),
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationFrom_ClientState':
response.xpath("//*[@id='ContentPlaceHolder1_meeDateOfRegistrationFrom_ClientState']/@value").get(),
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationFrom': "01/07/2020",
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationTo_ClientState':
response.xpath("//*[@id='ContentPlaceHolder1_meeDateOfRegistrationTo_ClientState']/@value").get(),
#'ContentPlaceHolder1_txtDateOfRegistrationTo': "03/07/2020",
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationTo': "03/07/2020",
'ctl00$ContentPlaceHolder1$ddlDistrict': "19409",
'ctl00$ContentPlaceHolder1$ddlPoliceStation': "",
'ctl00$ContentPlaceHolder1$txtFirno': "",
'ctl00$ContentPlaceHolder1$btnSearch': "Search",
'ctl00$ContentPlaceHolder1$ucRecordView$ddlPageSize': "0",
'ctl00$ContentPlaceHolder1$ucGridRecordView$txtPageNumber': ""
},
callback=(self.after_login),
)
def after_login(self, response):
police_stations = response.xpath(
'//*[@id="ContentPlaceHolder1_lbltotalrecord"]/text()').get()
print(police_stations)
# --- run without project and save in `output.csv` ---
from scrapy.crawler import CrawlerProcess
c = CrawlerProcess({
'USER_AGENT': 'Mozilla/5.0',
})
c.crawl(abcSpider)
c.start()
编辑： 带有值的代码给出了结果，但我不知道值多长时间是正确的以及它们是否适用于不同的日期
#!/usr/bin/env python3
import scrapy
from scrapy import FormRequest
class abcSpider(scrapy.Spider):
name = 'abc'
allowed_domains = ['citizen.mahapolice.gov.in']
def start_requests(self):
yield scrapy.Request(
url='https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
headers={
'Referer': 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx'
},
callback=self.parse
)
def parse(self, response):
yield FormRequest.from_response(
response,
formid='form1',
formdata={
'__EVENTTARGET': '',
'__EVENTARGUMENT': '',
'__LASTFOCUS': '',
'__VIEWSTATE': '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',
'__VIEWSTATEGENERATOR': '6F2EA376',
'__PREVIOUSPAGE': '6Fkypj_FbKCMscMOIEbFwiAIl-t4XMDVxhwkenT13SdXVANmcLkeKVNreNUcxzCFPd2Pxt-oh_2N7OVcM2YpQJ9h0re0OFqkn5XLvLpF1J-DFQ0h0',
'__EVENTVALIDATION': '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',
'ctl00$hdnSessionIdleTime': '',
'ctl00$hdnUserUniqueId': '',
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationFrom': '01/07/2020',
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationFrom_ClientState': '',
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationTo': '03/07/2020',
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationTo_ClientState': '',
'ctl00$ContentPlaceHolder1$ddlDistrict': '19372',
'ctl00$ContentPlaceHolder1$ddlPoliceStation': 'Select',
'ctl00$ContentPlaceHolder1$txtFirno': '',
'ctl00$ContentPlaceHolder1$btnSearch': 'Search',
'ctl00$ContentPlaceHolder1$ucRecordView$ddlPageSize': '0',
'ctl00$ContentPlaceHolder1$ucGridRecordView$txtPageNumber': '',
},
callback=(self.after_login),
)
def after_login(self, response):
police_stations = response.xpath(
'//*[@id="ContentPlaceHolder1_lbltotalrecord"]/text()').get()
print(police_stations)
# --- run without project and save in `output.csv` ---
from scrapy.crawler import CrawlerProcess
c = CrawlerProcess({
'USER_AGENT': 'Mozilla/5.0',
})
c.crawl(abcSpider)
c.start()
注:
我正在抓取的页面直到我现在所在的位置才使用 javascript。我也试过使用 scrapy_splash 但得到了同样的错误！ 我依靠 this 课程来启动蜘蛛。
问题：
scrapy spider 报错：
raise TypeError('to_bytes must receive a str or bytes '
TypeError: to_bytes must receive a str or bytes object, got Selector
我想要的：
作为输出的字符串，其中包括“一些记录”。
我尝试了什么？
我的代码：
import scrapy
from scrapy import FormRequest
class abcSpider(scrapy.Spider):
name = 'abc'
allowed_domains = ['citizen.mahapolice.gov.in']
def start_requests(self):
yield scrapy.Request(
url='http://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
headers={
'Referer': 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx'
},
callback=self.parse
)
def parse(self, response):
yield FormRequest.from_response(
response,
formid='form1',
formdata={
'__EVENTTARGET': response.xpath("//input[@name='__EVENTTARGET']/@value"),
'__EVENTARGUMENT': response.xpath("//*[@id='__EVENTARGUMENT']/@value"),
'__LASTFOCUS': response.xpath("//*[@id='__LASTFOCUS']/@value"),
'__VIEWSTATE':response.xpath("//*[@id='__VIEWSTATE']/@value"),
'__VIEWSTATEGENERATOR': "6F2EA376",
'__PREVIOUSPAGE': response.xpath("//*[@id='__PREVIOUSPAGE']/@value"),
'__EVENTVALIDATION': response.xpath("//*[@id='__EVENTVALIDATION']/@value"),
'ctl00$hdnSessionIdleTime': response.xpath("//*[@id='hdnSessionIdleTime']/@value"),
'ctl00$hdnUserUniqueId': response.xpath("//*[@id='hdnUserUniqueId']/@value"),
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationFrom_ClientState': response.xpath(
"//*[@id='ContentPlaceHolder1_meeDateOfRegistrationFrom_ClientState']/@value"),
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationFrom': "01/07/2020",
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationTo_ClientState':
response.xpath(
"//*[@id='ContentPlaceHolder1_meeDateOfRegistrationTo_ClientState']/@value"),
'ctl00$ContentPlaceHolder1_txtDateOfRegistrationTo': "03/07/2020",
'ctl00$ContentPlaceHolder1$ddlDistrict': "19409",
'ctl00$ContentPlaceHolder1$ddlPoliceStation': "",
'ctl00$ContentPlaceHolder1$txtFirno': "",
'ctl00$ContentPlaceHolder1$btnSearch': "Search",
'ctl00$ContentPlaceHolder1$ucRecordView$ddlPageSize': "0",
'ctl00$ContentPlaceHolder1$ucGridRecordView$txtPageNumber': ""
},
callback=(self.after_login),
)
def after_login(self, response):
police_stations = response.xpath(
'//*[@id="ContentPlaceHolder1_lbltotalrecord"]/text()').get()
print(police_stations)
终端输出：
2020-07-15 15:11:37 [scrapy.utils.log] INFO: Scrapy 2.2.0 started (bot: xyz)
2020-07-15 15:11:37 [scrapy.utils.log] INFO: Versions: lxml 4.5.0.0, libxml2 2.9.10, cssselect 1.1.0, parsel 1.6.0, w3lib 1.22.0, Twisted 20.3.0, Python 3.8.2 (default, Apr 27 2020, 15:53:34) - [GCC 9.3.0], pyOpenSSL 19.1.0 (OpenSSL 1.1.1f 31 Mar 2020), cryptography 2.8, Platform Linux-5.4.0-40-generic-x86_64-with-glibc2.29
2020-07-15 15:11:37 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.epollreactor.EPollReactor
2020-07-15 15:11:37 [scrapy.crawler] INFO: Overridden settings:
{'BOT_NAME': 'xyz',
'NEWSPIDER_MODULE': 'xyz.spiders',
'SPIDER_MODULES': ['xyz.spiders']}
2020-07-15 15:11:38 [scrapy.extensions.telnet] INFO: Telnet Password: db3dd9550774d0ab
2020-07-15 15:11:38 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.memusage.MemoryUsage',
'scrapy.extensions.logstats.LogStats']
2020-07-15 15:11:39 [scrapy.middleware] INFO: Enabled downloader middlewares:
['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']
2020-07-15 15:11:39 [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']
2020-07-15 15:11:39 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2020-07-15 15:11:39 [scrapy.core.engine] INFO: Spider opened
2020-07-15 15:11:39 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2020-07-15 15:11:39 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2020-07-15 15:11:40 [scrapy.downloadermiddlewares.redirect] DEBUG: Redirecting (302) to <GET https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx> from <GET http://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx>
2020-07-15 15:11:40 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx> (referer: https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx)
2020-07-15 15:11:40 [scrapy.core.scraper] ERROR: Spider error processing <GET https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx> (referer: https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx)
Traceback (most recent call last):
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/defer.py", line 120, in iter_errback
yield next(it)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/python.py", line 346, in __next__
return next(self.data)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/python.py", line 346, in __next__
return next(self.data)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output
for x in result:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/referer.py", line 340, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr>
return (r for r in result or () if _filter(r))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr>
return (r for r in result or () if _filter(r))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/core/spidermw.py", line 64, in _evaluate_iterable
for r in iterable:
File "/home/sangharshmanuski/Documents/delet/xyz/xyz/spiders/abc.py", line 20, in parse
yield FormRequest.from_response(
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 58, in from_response
return cls(url=url, method=method, formdata=formdata, **kwargs)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 31, in __init__
querystr = _urlencode(items, self.encoding)
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 71, in _urlencode
values = [(to_bytes(k, enc), to_bytes(v, enc))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/http/request/form.py", line 71, in <listcomp>
values = [(to_bytes(k, enc), to_bytes(v, enc))
File "/home/sangharshmanuski/.local/lib/python3.8/site-packages/scrapy/utils/python.py", line 104, in to_bytes
raise TypeError('to_bytes must receive a str or bytes '
TypeError: to_bytes must receive a str or bytes object, got Selector
2020-07-15 15:11:40 [scrapy.core.engine] INFO: Closing spider (finished)
2020-07-15 15:11:40 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 648,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 8150,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/302': 1,
'elapsed_time_seconds': 1.116569,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2020, 7, 15, 9, 41, 40, 607840),
'log_count/DEBUG': 2,
'log_count/ERROR': 1,
'log_count/INFO': 10,
'memusage/max': 52281344,
'memusage/startup': 52281344,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'spider_exceptions/TypeError': 1,
'start_time': datetime.datetime(2020, 7, 15, 9, 41, 39, 491271)}
2020-07-15 15:11:40 [scrapy.core.engine] INFO: Spider closed (finished)
你有问题，我在 previous question 的评论中提到过。
当您在 formdata={...}
response.xpath(...).get() 时，您必须使用 .get()
顺便说一句：
你的字段名还是有误
'ContentPlaceHolder1_txtDateOfRegistrationTo': "03/07/2020",
必须
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationTo': "03/07/2020",
并且您必须在开始 url 时使用 https:// 而不是 http://。
url = 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
如果你使用 http:// 那么它会重定向到主页
https://citizen.mahapolice.gov.in/Citizen/MH/index.aspx
然后您将表单发送到 index.aspx 而不是 PublishedFIRs.aspx
可以放在一个文件中的最少工作代码 运行 python script.py 而不会产生问题
它没有以前的错误，它发送到更正 url 但它仍然有值 __VIEWSTATE 和 __EVENTVALIDATION 的问题。如果我从网络浏览器复制所有值然后它工作但如果我使用来自 scrapy 的值然后页面生成错误 500。可能页面使用 JavaScript 生成这些值。
#!/usr/bin/env python3
import scrapy
from scrapy import FormRequest
class abcSpider(scrapy.Spider):
name = 'abc'
allowed_domains = ['citizen.mahapolice.gov.in']
def start_requests(self):
yield scrapy.Request(
url='https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
headers={
'USER_AGENT': 'Mozilla/5.0',
'Referer': 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx'
},
callback=self.parse
)
def parse(self, response):
yield FormRequest.from_response(
response,
formid='form1',
formdata={
'__EVENTTARGET': response.xpath("//input[@name='__EVENTTARGET']/@value").get(),
'__EVENTARGUMENT': response.xpath("//*[@id='__EVENTARGUMENT']/@value").get(),
'__LASTFOCUS': response.xpath("//*[@id='__LASTFOCUS']/@value").get(),
'__VIEWSTATE':response.xpath("//*[@id='__VIEWSTATE']/@value").get(),
'__VIEWSTATEGENERATOR': "6F2EA376",
'__PREVIOUSPAGE': response.xpath("//*[@id='__PREVIOUSPAGE']/@value").get(),
'__EVENTVALIDATION': response.xpath("//*[@id='__EVENTVALIDATION']/@value").get(),
'ctl00$hdnSessionIdleTime': response.xpath("//*[@id='hdnSessionIdleTime']/@value").get(),
'ctl00$hdnUserUniqueId': response.xpath("//*[@id='hdnUserUniqueId']/@value").get(),
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationFrom_ClientState':
response.xpath("//*[@id='ContentPlaceHolder1_meeDateOfRegistrationFrom_ClientState']/@value").get(),
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationFrom': "01/07/2020",
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationTo_ClientState':
response.xpath("//*[@id='ContentPlaceHolder1_meeDateOfRegistrationTo_ClientState']/@value").get(),
#'ContentPlaceHolder1_txtDateOfRegistrationTo': "03/07/2020",
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationTo': "03/07/2020",
'ctl00$ContentPlaceHolder1$ddlDistrict': "19409",
'ctl00$ContentPlaceHolder1$ddlPoliceStation': "",
'ctl00$ContentPlaceHolder1$txtFirno': "",
'ctl00$ContentPlaceHolder1$btnSearch': "Search",
'ctl00$ContentPlaceHolder1$ucRecordView$ddlPageSize': "0",
'ctl00$ContentPlaceHolder1$ucGridRecordView$txtPageNumber': ""
},
callback=(self.after_login),
)
def after_login(self, response):
police_stations = response.xpath(
'//*[@id="ContentPlaceHolder1_lbltotalrecord"]/text()').get()
print(police_stations)
# --- run without project and save in `output.csv` ---
from scrapy.crawler import CrawlerProcess
c = CrawlerProcess({
'USER_AGENT': 'Mozilla/5.0',
})
c.crawl(abcSpider)
c.start()
编辑： 带有值的代码给出了结果，但我不知道值多长时间是正确的以及它们是否适用于不同的日期
#!/usr/bin/env python3
import scrapy
from scrapy import FormRequest
class abcSpider(scrapy.Spider):
name = 'abc'
allowed_domains = ['citizen.mahapolice.gov.in']
def start_requests(self):
yield scrapy.Request(
url='https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx',
headers={
'Referer': 'https://citizen.mahapolice.gov.in/Citizen/MH/PublishedFIRs.aspx'
},
callback=self.parse
)
def parse(self, response):
yield FormRequest.from_response(
response,
formid='form1',
formdata={
'__EVENTTARGET': '',
'__EVENTARGUMENT': '',
'__LASTFOCUS': '',
'__VIEWSTATE': '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',
'__VIEWSTATEGENERATOR': '6F2EA376',
'__PREVIOUSPAGE': '6Fkypj_FbKCMscMOIEbFwiAIl-t4XMDVxhwkenT13SdXVANmcLkeKVNreNUcxzCFPd2Pxt-oh_2N7OVcM2YpQJ9h0re0OFqkn5XLvLpF1J-DFQ0h0',
'__EVENTVALIDATION': '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',
'ctl00$hdnSessionIdleTime': '',
'ctl00$hdnUserUniqueId': '',
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationFrom': '01/07/2020',
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationFrom_ClientState': '',
'ctl00$ContentPlaceHolder1$txtDateOfRegistrationTo': '03/07/2020',
'ctl00$ContentPlaceHolder1$meeDateOfRegistrationTo_ClientState': '',
'ctl00$ContentPlaceHolder1$ddlDistrict': '19372',
'ctl00$ContentPlaceHolder1$ddlPoliceStation': 'Select',
'ctl00$ContentPlaceHolder1$txtFirno': '',
'ctl00$ContentPlaceHolder1$btnSearch': 'Search',
'ctl00$ContentPlaceHolder1$ucRecordView$ddlPageSize': '0',
'ctl00$ContentPlaceHolder1$ucGridRecordView$txtPageNumber': '',
},
callback=(self.after_login),
)
def after_login(self, response):
police_stations = response.xpath(
'//*[@id="ContentPlaceHolder1_lbltotalrecord"]/text()').get()
print(police_stations)
# --- run without project and save in `output.csv` ---
from scrapy.crawler import CrawlerProcess
c = CrawlerProcess({
'USER_AGENT': 'Mozilla/5.0',
})
c.crawl(abcSpider)
c.start()