Ausgabe der neuen DB Einträge

venv/lib/python3.9/site-packages/scrapy/http/request/__init__.py

@@ -0,0 +1,143 @@
+"""
+This module implements the Request class which is used to represent HTTP
+requests in Scrapy.
+
+See documentation in docs/topics/request-response.rst
+"""
+from w3lib.url import safe_url_string
+
+from scrapy.http.headers import Headers
+from scrapy.utils.python import to_bytes
+from scrapy.utils.trackref import object_ref
+from scrapy.utils.url import escape_ajax
+from scrapy.http.common import obsolete_setter
+from scrapy.utils.curl import curl_to_request_kwargs
+
+
+class Request(object_ref):
+
+    def __init__(self, url, callback=None, method='GET', headers=None, body=None,
+                 cookies=None, meta=None, encoding='utf-8', priority=0,
+                 dont_filter=False, errback=None, flags=None, cb_kwargs=None):
+
+        self._encoding = encoding  # this one has to be set first
+        self.method = str(method).upper()
+        self._set_url(url)
+        self._set_body(body)
+        if not isinstance(priority, int):
+            raise TypeError(f"Request priority not an integer: {priority!r}")
+        self.priority = priority
+
+        if callback is not None and not callable(callback):
+            raise TypeError(f'callback must be a callable, got {type(callback).__name__}')
+        if errback is not None and not callable(errback):
+            raise TypeError(f'errback must be a callable, got {type(errback).__name__}')
+        self.callback = callback
+        self.errback = errback
+
+        self.cookies = cookies or {}
+        self.headers = Headers(headers or {}, encoding=encoding)
+        self.dont_filter = dont_filter
+
+        self._meta = dict(meta) if meta else None
+        self._cb_kwargs = dict(cb_kwargs) if cb_kwargs else None
+        self.flags = [] if flags is None else list(flags)
+
+    @property
+    def cb_kwargs(self):
+        if self._cb_kwargs is None:
+            self._cb_kwargs = {}
+        return self._cb_kwargs
+
+    @property
+    def meta(self):
+        if self._meta is None:
+            self._meta = {}
+        return self._meta
+
+    def _get_url(self):
+        return self._url
+
+    def _set_url(self, url):
+        if not isinstance(url, str):
+            raise TypeError(f'Request url must be str or unicode, got {type(url).__name__}')
+
+        s = safe_url_string(url, self.encoding)
+        self._url = escape_ajax(s)
+
+        if (
+            '://' not in self._url
+            and not self._url.startswith('about:')
+            and not self._url.startswith('data:')
+        ):
+            raise ValueError(f'Missing scheme in request url: {self._url}')
+
+    url = property(_get_url, obsolete_setter(_set_url, 'url'))
+
+    def _get_body(self):
+        return self._body
+
+    def _set_body(self, body):
+        if body is None:
+            self._body = b''
+        else:
+            self._body = to_bytes(body, self.encoding)
+
+    body = property(_get_body, obsolete_setter(_set_body, 'body'))
+
+    @property
+    def encoding(self):
+        return self._encoding
+
+    def __str__(self):
+        return f"<{self.method} {self.url}>"
+
+    __repr__ = __str__
+
+    def copy(self):
+        """Return a copy of this Request"""
+        return self.replace()
+
+    def replace(self, *args, **kwargs):
+        """Create a new Request with the same attributes except for those
+        given new values.
+        """
+        for x in ['url', 'method', 'headers', 'body', 'cookies', 'meta', 'flags',
+                  'encoding', 'priority', 'dont_filter', 'callback', 'errback', 'cb_kwargs']:
+            kwargs.setdefault(x, getattr(self, x))
+        cls = kwargs.pop('cls', self.__class__)
+        return cls(*args, **kwargs)
+
+    @classmethod
+    def from_curl(cls, curl_command, ignore_unknown_options=True, **kwargs):
+        """Create a Request object from a string containing a `cURL
+        <https://curl.haxx.se/>`_ command. It populates the HTTP method, the
+        URL, the headers, the cookies and the body. It accepts the same
+        arguments as the :class:`Request` class, taking preference and
+        overriding the values of the same arguments contained in the cURL
+        command.
+
+        Unrecognized options are ignored by default. To raise an error when
+        finding unknown options call this method by passing
+        ``ignore_unknown_options=False``.
+
+        .. caution:: Using :meth:`from_curl` from :class:`~scrapy.http.Request`
+                     subclasses, such as :class:`~scrapy.http.JSONRequest`, or
+                     :class:`~scrapy.http.XmlRpcRequest`, as well as having
+                     :ref:`downloader middlewares <topics-downloader-middleware>`
+                     and
+                     :ref:`spider middlewares <topics-spider-middleware>`
+                     enabled, such as
+                     :class:`~scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware`,
+                     :class:`~scrapy.downloadermiddlewares.useragent.UserAgentMiddleware`,
+                     or
+                     :class:`~scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware`,
+                     may modify the :class:`~scrapy.http.Request` object.
+
+        To translate a cURL command into a Scrapy request,
+        you may use `curl2scrapy <https://michael-shub.github.io/curl2scrapy/>`_.
+
+       """
+        request_kwargs = curl_to_request_kwargs(curl_command, ignore_unknown_options)
+        request_kwargs.update(kwargs)
+        return cls(**request_kwargs)

venv/lib/python3.9/site-packages/scrapy/http/request/form.py

@@ -0,0 +1,215 @@
+"""
+This module implements the FormRequest class which is a more convenient class
+(than Request) to generate Requests based on form data.
+
+See documentation in docs/topics/request-response.rst
+"""
+
+from urllib.parse import urljoin, urlencode
+
+import lxml.html
+from parsel.selector import create_root_node
+from w3lib.html import strip_html5_whitespace
+
+from scrapy.http.request import Request
+from scrapy.utils.python import to_bytes, is_listlike
+from scrapy.utils.response import get_base_url
+
+
+class FormRequest(Request):
+    valid_form_methods = ['GET', 'POST']
+
+    def __init__(self, *args, **kwargs):
+        formdata = kwargs.pop('formdata', None)
+        if formdata and kwargs.get('method') is None:
+            kwargs['method'] = 'POST'
+
+        super().__init__(*args, **kwargs)
+
+        if formdata:
+            items = formdata.items() if isinstance(formdata, dict) else formdata
+            querystr = _urlencode(items, self.encoding)
+            if self.method == 'POST':
+                self.headers.setdefault(b'Content-Type', b'application/x-www-form-urlencoded')
+                self._set_body(querystr)
+            else:
+                self._set_url(self.url + ('&' if '?' in self.url else '?') + querystr)
+
+    @classmethod
+    def from_response(cls, response, formname=None, formid=None, formnumber=0, formdata=None,
+                      clickdata=None, dont_click=False, formxpath=None, formcss=None, **kwargs):
+
+        kwargs.setdefault('encoding', response.encoding)
+
+        if formcss is not None:
+            from parsel.csstranslator import HTMLTranslator
+            formxpath = HTMLTranslator().css_to_xpath(formcss)
+
+        form = _get_form(response, formname, formid, formnumber, formxpath)
+        formdata = _get_inputs(form, formdata, dont_click, clickdata, response)
+        url = _get_form_url(form, kwargs.pop('url', None))
+
+        method = kwargs.pop('method', form.method)
+        if method is not None:
+            method = method.upper()
+            if method not in cls.valid_form_methods:
+                method = 'GET'
+
+        return cls(url=url, method=method, formdata=formdata, **kwargs)
+
+
+def _get_form_url(form, url):
+    if url is None:
+        action = form.get('action')
+        if action is None:
+            return form.base_url
+        return urljoin(form.base_url, strip_html5_whitespace(action))
+    return urljoin(form.base_url, url)
+
+
+def _urlencode(seq, enc):
+    values = [(to_bytes(k, enc), to_bytes(v, enc))
+              for k, vs in seq
+              for v in (vs if is_listlike(vs) else [vs])]
+    return urlencode(values, doseq=1)
+
+
+def _get_form(response, formname, formid, formnumber, formxpath):
+    """Find the form element """
+    root = create_root_node(response.text, lxml.html.HTMLParser,
+                            base_url=get_base_url(response))
+    forms = root.xpath('//form')
+    if not forms:
+        raise ValueError(f"No <form> element found in {response}")
+
+    if formname is not None:
+        f = root.xpath(f'//form[@name="{formname}"]')
+        if f:
+            return f[0]
+
+    if formid is not None:
+        f = root.xpath(f'//form[@id="{formid}"]')
+        if f:
+            return f[0]
+
+    # Get form element from xpath, if not found, go up
+    if formxpath is not None:
+        nodes = root.xpath(formxpath)
+        if nodes:
+            el = nodes[0]
+            while True:
+                if el.tag == 'form':
+                    return el
+                el = el.getparent()
+                if el is None:
+                    break
+        raise ValueError(f'No <form> element found with {formxpath}')
+
+    # If we get here, it means that either formname was None
+    # or invalid
+    if formnumber is not None:
+        try:
+            form = forms[formnumber]
+        except IndexError:
+            raise IndexError(f"Form number {formnumber} not found in {response}")
+        else:
+            return form
+
+
+def _get_inputs(form, formdata, dont_click, clickdata, response):
+    try:
+        formdata_keys = dict(formdata or ()).keys()
+    except (ValueError, TypeError):
+        raise ValueError('formdata should be a dict or iterable of tuples')
+
+    if not formdata:
+        formdata = ()
+    inputs = form.xpath('descendant::textarea'
+                        '|descendant::select'
+                        '|descendant::input[not(@type) or @type['
+                        ' not(re:test(., "^(?:submit|image|reset)$", "i"))'
+                        ' and (../@checked or'
+                        '  not(re:test(., "^(?:checkbox|radio)$", "i")))]]',
+                        namespaces={
+                            "re": "http://exslt.org/regular-expressions"})
+    values = [(k, '' if v is None else v)
+              for k, v in (_value(e) for e in inputs)
+              if k and k not in formdata_keys]
+
+    if not dont_click:
+        clickable = _get_clickable(clickdata, form)
+        if clickable and clickable[0] not in formdata and not clickable[0] is None:
+            values.append(clickable)
+
+    if isinstance(formdata, dict):
+        formdata = formdata.items()
+
+    values.extend((k, v) for k, v in formdata if v is not None)
+    return values
+
+
+def _value(ele):
+    n = ele.name
+    v = ele.value
+    if ele.tag == 'select':
+        return _select_value(ele, n, v)
+    return n, v
+
+
+def _select_value(ele, n, v):
+    multiple = ele.multiple
+    if v is None and not multiple:
+        # Match browser behaviour on simple select tag without options selected
+        # And for select tags wihout options
+        o = ele.value_options
+        return (n, o[0]) if o else (None, None)
+    elif v is not None and multiple:
+        # This is a workround to bug in lxml fixed 2.3.1
+        # fix https://github.com/lxml/lxml/commit/57f49eed82068a20da3db8f1b18ae00c1bab8b12#L1L1139
+        selected_options = ele.xpath('.//option[@selected]')
+        v = [(o.get('value') or o.text or '').strip() for o in selected_options]
+    return n, v
+
+
+def _get_clickable(clickdata, form):
+    """
+    Returns the clickable element specified in clickdata,
+    if the latter is given. If not, it returns the first
+    clickable element found
+    """
+    clickables = list(form.xpath(
+        'descendant::input[re:test(@type, "^(submit|image)$", "i")]'
+        '|descendant::button[not(@type) or re:test(@type, "^submit$", "i")]',
+        namespaces={"re": "http://exslt.org/regular-expressions"}
+    ))
+    if not clickables:
+        return
+
+    # If we don't have clickdata, we just use the first clickable element
+    if clickdata is None:
+        el = clickables[0]
+        return (el.get('name'), el.get('value') or '')
+
+    # If clickdata is given, we compare it to the clickable elements to find a
+    # match. We first look to see if the number is specified in clickdata,
+    # because that uniquely identifies the element
+    nr = clickdata.get('nr', None)
+    if nr is not None:
+        try:
+            el = list(form.inputs)[nr]
+        except IndexError:
+            pass
+        else:
+            return (el.get('name'), el.get('value') or '')
+
+    # We didn't find it, so now we build an XPath expression out of the other
+    # arguments, because they can be used as such
+    xpath = './/*' + ''.join(f'[@{k}="{v}"]' for k, v in clickdata.items())
+    el = form.xpath(xpath)
+    if len(el) == 1:
+        return (el[0].get('name'), el[0].get('value') or '')
+    elif len(el) > 1:
+        raise ValueError(f"Multiple elements found ({el!r}) matching the "
+                         f"criteria in clickdata: {clickdata!r}")
+    else:
+        raise ValueError(f'No clickable element matching clickdata: {clickdata!r}')

venv/lib/python3.9/site-packages/scrapy/http/request/json_request.py

@@ -0,0 +1,57 @@
+"""
+This module implements the JsonRequest class which is a more convenient class
+(than Request) to generate JSON Requests.
+
+See documentation in docs/topics/request-response.rst
+"""
+
+import copy
+import json
+import warnings
+
+from scrapy.http.request import Request
+from scrapy.utils.deprecate import create_deprecated_class
+
+
+class JsonRequest(Request):
+    def __init__(self, *args, **kwargs):
+        dumps_kwargs = copy.deepcopy(kwargs.pop('dumps_kwargs', {}))
+        dumps_kwargs.setdefault('sort_keys', True)
+        self._dumps_kwargs = dumps_kwargs
+
+        body_passed = kwargs.get('body', None) is not None
+        data = kwargs.pop('data', None)
+        data_passed = data is not None
+
+        if body_passed and data_passed:
+            warnings.warn('Both body and data passed. data will be ignored')
+
+        elif not body_passed and data_passed:
+            kwargs['body'] = self._dumps(data)
+
+            if 'method' not in kwargs:
+                kwargs['method'] = 'POST'
+
+        super().__init__(*args, **kwargs)
+        self.headers.setdefault('Content-Type', 'application/json')
+        self.headers.setdefault('Accept', 'application/json, text/javascript, */*; q=0.01')
+
+    def replace(self, *args, **kwargs):
+        body_passed = kwargs.get('body', None) is not None
+        data = kwargs.pop('data', None)
+        data_passed = data is not None
+
+        if body_passed and data_passed:
+            warnings.warn('Both body and data passed. data will be ignored')
+
+        elif not body_passed and data_passed:
+            kwargs['body'] = self._dumps(data)
+
+        return super().replace(*args, **kwargs)
+
+    def _dumps(self, data):
+        """Convert to JSON """
+        return json.dumps(data, **self._dumps_kwargs)
+
+
+JSONRequest = create_deprecated_class("JSONRequest", JsonRequest)

venv/lib/python3.9/site-packages/scrapy/http/request/rpc.py

@@ -0,0 +1,35 @@
+"""
+This module implements the XmlRpcRequest class which is a more convenient class
+(that Request) to generate xml-rpc requests.
+
+See documentation in docs/topics/request-response.rst
+"""
+import xmlrpc.client as xmlrpclib
+
+from scrapy.http.request import Request
+from scrapy.utils.python import get_func_args
+
+
+DUMPS_ARGS = get_func_args(xmlrpclib.dumps)
+
+
+class XmlRpcRequest(Request):
+
+    def __init__(self, *args, **kwargs):
+        encoding = kwargs.get('encoding', None)
+        if 'body' not in kwargs and 'params' in kwargs:
+            kw = dict((k, kwargs.pop(k)) for k in DUMPS_ARGS if k in kwargs)
+            kwargs['body'] = xmlrpclib.dumps(**kw)
+
+        # spec defines that requests must use POST method
+        kwargs.setdefault('method', 'POST')
+
+        # xmlrpc query multiples times over the same url
+        kwargs.setdefault('dont_filter', True)
+
+        # restore encoding
+        if encoding is not None:
+            kwargs['encoding'] = encoding
+
+        super().__init__(*args, **kwargs)
+        self.headers.setdefault('Content-Type', 'text/xml')