def test_request_ua():
headers = {
"User-Agent": "Python3.5"
}
request = Request('http://www.httpbin.org/get', method='GET', res_type='json', headers=headers)
result = asyncio.get_event_loop().run_until_complete(request.fetch())
assert result.html['headers']['User-Agent'] == "Python3.5"
def test_method_error_request():
try:
request = Request("https://httpbin.org/", method="PUT")
response = asyncio.get_event_loop().run_until_complete(request.fetch())
assert await response.text() == ""
except Exception as e:
assert isinstance(e, InvalidRequestMethod)
async def _localImage_or_webImage_parse(self, request: Request,
spider_ins):
'''
process image-data(loacl-image or web-image) during middle.request
:param request: Request
'''
_raw_url = request.url
if _raw_url.startswith('https'):
logger.error('Baidu-ocr does not support remote https image link,'
'check your start_urls')
request.retry_times = 0
raise ImageTypeError
elif _raw_url.startswith('http'):
# self._service_payload.update(url=_raw_url)
self._service_payload.pop('image', None)
self._service_payload.update(url=_raw_url)
else:
if _raw_url[-3:] not in ['jpg', 'png', 'bmp', 'peg']:
logger.error('Baidu does not support this type of picture , '
'must be `jpg`, `png`, `bmp` or `jpeg`')
request.retry_times = 0
request._ok = False
raise ImageTypeError
else:
image, _path = await self.get_ocr_image(
_raw_url,
request,
spider_ins,
hook=self.get_ocr_image_hook,
region=spider_ins.ocr_options['region'])
self._service_payload.pop('url', None)
self._service_payload.update(image=image)
def test_method_error_request():
try:
request = Request('https://httpbin.org/', method='PUT')
response = asyncio.get_event_loop().run_until_complete(request.fetch())
assert response.html == ''
except Exception as e:
assert isinstance(e, InvalidRequestMethod)
def test_request_params():
params = {
"name": "ruia"
}
request = Request('http://www.httpbin.org/get', method='GET', res_type='json', params=params)
result = asyncio.get_event_loop().run_until_complete(request.fetch())
assert result.html['args']['name'] == "ruia"
def test_delay_false():
request_config = {"DELAY": 10}
request = Request("https://httpbin.org/", request_config=request_config)
# Start a timer to time request
timer = time.time()
response = asyncio.get_event_loop().run_until_complete(request.fetch(delay=False))
# Ensure delay option was ignored (time taken is less than 10s)
assert time.time() - timer < 10
async def sec_request():
form_data, must_cookies, history = await request_example()
headers = {
'User-Agent': ('Mozilla/5.0'),
}
request = Request(url='http://portal.neaea.gov.et/Student/StudentDetailsx',
method='POST',
headers=headers,
metadata=form_data,
cookies=must_cookies)
print(request)
return request.fetch()
def test_retry_delay():
# Test invalid URL (to trigger retries) with 1s delay between retries
request_config = {"RETRIES": 2, "RETRY_DELAY": 1}
request = Request("http://127.0.0.1:5999/", request_config=request_config)
# Start a timer to time retries
timer = time.time()
_, response = asyncio.get_event_loop().run_until_complete(
request.fetch_callback(sem=sem))
# Ensure that for 2 retries the time taken is > 2s (1s between each retry)
assert time.time() - timer > 2
async def request_example():
url = 'http://portal.neaea.gov.et/Home/Student'
params = {
'name': 'ruia',
}
headers = {
'User-Agent': ('Mozilla/5.0'),
}
request = Request(url=url, method='GET', params=params, headers=headers)
must_cookies = {}
must_cookies_names = ['__RequestVerificationToken']
response = await request.fetch()
for cookie_name in must_cookies_names:
must_cookies[cookie_name] = response.cookies.get(cookie_name)
history = response.history
text = await response.text()
html = Selector(text=text)
csrf_token = html.xpath("/html/body/div[2]/div/form/input/@value").get()
form_data = {
'__RequestVerificationToken': csrf_token,
'admissionNumber': None # to be set
}
return form_data, must_cookies, history
async def async_fetch(
self,
url_or_request: Union[Request, str],
response: Response = None,
):
"""
Fetch target URL
:param url_or_request:
:param response:
:return:
"""
async with aiohttp.ClientSession() as session:
if isinstance(url_or_request, Request):
request: Request = url_or_request
request.request_session = session
else:
request: Request = Request(url=url_or_request,
request_session=session)
if response is None:
response: Response = await request.fetch()
# process response
response.html = await response.text()
response.etree = response.html_etree(response.html)
self.refresh_user_ns(request, response)
async def parse(self, response):
for index, url in enumerate(self.start_urls):
yield Request(url,
method='POST',
data=self.body,
callback=self.parse_item,
metadata={'index': index})
async def parse(self, response):
yield Request(
url=response.url,
callback=self.parse_item,
headers=self.headers,
request_config=self.request_config,
**self.kwargs
)
async def make_post_request(sem, callback):
headers = {'Content-Type': 'application/json'}
request = Request('https://httpbin.org/post',
method='POST',
headers=headers,
data=params,
callback=callback)
return await request.fetch_callback(sem)
async def parse(self, res):
pages = ['http://www.httpbin.org/get', 'http://www.httpbin.org/get']
for index, page in enumerate(pages):
yield Request(
page,
callback=self.parse_item,
metadata={'index': index}
)
async def parse(self, response):
self.mongo_db = MotorBase().get_db('ruia_test')
urls = ['https://news.ycombinator.com/news?p=1', 'https://news.ycombinator.com/news?p=2']
for index, url in enumerate(urls):
yield Request(
url,
callback=self.parse_item,
metadata={'index': index}
)
async def parse(self, res):
items = await alist(ArchivesItem.get_items(html=res.html))
self.mongo_db = MotorBase(loop=self.loop).get_db()
for item in items:
# 随机休眠
self.request_config['DELAY'] = random.randint(5, 10)
yield Request(item.href,
callback=self.parse_item,
request_config=self.request_config)
async def request_example():
url = "https://httpbin.org/get"
params = {"name": "ruia"}
headers = {"User-Agent": "Python3.6"}
request = Request(
url=url, method="GET", res_type="json", params=params, headers=headers
)
response = await request.fetch()
assert response.html["args"]["name"] == "ruia"
assert response.html["headers"]["User-Agent"] == "Python3.6"
async def parse(self, response):
self.mongo_db = MotorBase().get_db('hacknews')
urls = ['https://baijiahao.baidu.com/s?id=1553475025395018',
'https://baijiahao.baidu.com/s?id=1570895803249513']
for index, url in enumerate(urls):
yield Request(
url,
callback=self.parse_item,
metadata={'index': index}
)
async def make_post_request(sem, callback):
headers = {"Content-Type": "application/json"}
request = Request(
"https://httpbin.org/post",
method="POST",
headers=headers,
data=params,
callback=callback,
)
return await request.fetch_callback(sem)
async def parse(self, response):
self.mongo_db = MotorBase().get_db("ruia_test")
urls = [
"https://news.ycombinator.com/news?p=1",
"https://news.ycombinator.com/news?p=2",
]
for index, url in enumerate(urls):
yield Request(url,
callback=self.parse_item,
metadata={"index": index})
async def parse(self, res):
try:
self.mongo_db = MotorBase(loop=self.loop).get_db()
except Exception as e:
self.logger.exception(e)
async for item in ArchivesItem.get_items(html=await res.text()):
yield Request(
item.href,
callback=self.parse_item,
request_config=self.request_config,
)
async def parse(self, res):
etree = res.html_etree
pages = ['?start=0&filter='
] + [i.get('href') for i in etree.cssselect('.paginator>a')]
for index, page in enumerate(pages):
url = self.start_urls[0] + page
yield Request(url,
callback=self.parse_item,
metadata={'index': index},
request_config=self.request_config,
**self.kwargs)
async def timeout_request(sem):
request_config = {"RETRIES": 1, "DELAY": 1, "TIMEOUT": 0.1}
request = Request(
"https://httpbin.org/get",
method="GET",
metadata={"hello": "ruia"},
encoding="utf-8",
request_config=request_config,
params=params,
callback=hi,
)
return await request.fetch_callback(sem)
def test_request_config():
assert str(Request("https://httpbin.org/")) == "<GET https://httpbin.org/>"
_, response = asyncio.get_event_loop().run_until_complete(
make_get_request(sem=sem, callback=hello))
# assert response.callback_result == "hello ruia"
assert response.metadata == {"hello": "ruia"}
json_result = asyncio.get_event_loop().run_until_complete(response.json())
assert json_result["args"]["name"] == "ruia"
_, response = asyncio.get_event_loop().run_until_complete(
make_post_request(sem=sem, callback=None))
json_result = asyncio.get_event_loop().run_until_complete(response.json())
assert json_result["data"] == "name=ruia"
def test_request_config():
assert str(Request('https://httpbin.org/')) == '<GET https://httpbin.org/>'
_, response = asyncio.get_event_loop().run_until_complete(
make_get_request(sem=sem, callback=hello))
assert response.callback_result == 'hello ruia'
assert response.metadata == {'hello': 'ruia'}
json_result = asyncio.get_event_loop().run_until_complete(response.json())
assert json_result['args']['name'] == "ruia"
_, response = asyncio.get_event_loop().run_until_complete(
make_post_request(sem=sem, callback=None))
json_result = asyncio.get_event_loop().run_until_complete(response.json())
assert json_result['data'] == "name=ruia"
async def parse(self, res):
etree = res.html_etree
urls = [
i.get('href') for i in etree.cssselect('.content_list .dd_bt a')
]
for index, url in enumerate(urls):
url = 'http:' + url
yield Request(
url,
callback=self.parse_item,
metadata={'index': index},
request_config=self.request_config,
)
async def parse_item(self, res):
async for item in ArticleListItem.get_items(html=await res.text()):
# 已经抓取的链接不再请求
is_exist = (await self.mongo_db.source_docs.find_one(
{"url": item.href}) or {})
if not is_exist.get("html"):
yield Request(
item.href,
callback=self.save,
metadata={"title": item.title},
request_config=self.request_config,
)
async def parse_item(self, res):
items = await alist(ArticleListItem.get_items(html=res.html))
for item in items:
# 已经抓取的链接不再请求
is_exist = await self.mongo_db.source_docs.find_one(
{'url': item.href})
if not is_exist:
# 随机休眠
self.request_config['DELAY'] = random.randint(5, 10)
yield Request(item.href,
callback=self.save,
metadata={'title': item.title},
request_config=self.request_config)
async def timeout_request(sem):
request_config = {
'RETRIES': 1,
'DELAY': 1,
'TIMEOUT': 0.1,
}
request = Request('https://httpbin.org/get',
method='GET',
metadata={'hello': 'ruia'},
encoding='utf-8',
request_config=request_config,
params=params,
callback=hi)
return await request.fetch_callback(sem)
async def parse_item(self, res):
items = await ArticleListItem.get_items(html=res.html)
for item in items:
# 已经抓取的链接不再请求
is_exist = await self.mongo_db.source_docs.find_one(
{'url': item.href}) or {}
if not is_exist.get('html'):
yield Request(
item.href,
callback=self.save,
metadata={'title': item.title},
request_config=self.request_config,
)