def __init__(self, url, cookies2=None, proxies=None, cookies=None):
self.url = url
self.proxies = proxies
self.email = SendEmail()
# cookies = cookies2 if cookies2 else self._get_cookies()
self.session = requests.Session()
self.session.cookies = cookiejar_from_dict(cookies) # session设置cookie
headers = {
'Accept':
'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding':
'gzip, deflate, br',
'Accept-Language':
'zh-CN,zh;q=0.9',
'Connection':
'keep-alive',
'Host':
'antirobot.tianyancha.com',
'Cookies':
cookies,
'Referer':
'https://antirobot.tianyancha.com/captcha/verify?return_url={}&rnd='
.format(self.url),
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
'X-CSRFToken':
'null',
'X-Requested-With':
'XMLHttpRequest',
}
def prepare_request(self, request):
"""Constructs a :class:`PreparedRequest <PreparedRequest>` for
transmission and returns it. The :class:`PreparedRequest` has settings
merged from the :class:`Request <Request>` instance and those of the
:class:`Session`.
:param request: :class:`Request` instance to prepare with this
session's settings.
:rtype: requests.PreparedRequest
"""
cookies = request.cookies or {}
# Bootstrap CookieJar.
if not isinstance(cookies, cookielib.CookieJar):
cookies = cookiejar_from_dict(cookies)
# Merge with session cookies
merged_cookies = merge_cookies(
merge_cookies(RequestsCookieJar(), self.cookies), cookies)
# Set environment's basic authentication if not explicitly set.
auth = request.auth
if self.trust_env and not auth and not self.auth:
auth = get_netrc_auth(request.url)
p = CuPreparedRequest()
p.prepare(
method=request.method.upper(),
url=request.url,
files=request.files,
data=request.data,
json=request.json,
headers=merge_setting(request.headers,
self.headers,
dict_class=CaseInsensitiveDict),
params=merge_setting(request.params, self.params),
auth=merge_setting(auth, self.auth),
cookies=merged_cookies,
hooks=merge_hooks(request.hooks, self.hooks),
)
return p
def __init__(self, num):
self.num = num
self.session = requests.session()
self.session.cookies = cookiejar_from_dict(DEFAULT_COOKIES[0])
self.headers = DEFAULT_HEADERS
self.tel = datas[num].get("phone", 0)
# 获取HMSACCOUNT的cookie
a = session.get(
f'https://hm.baidu.com/hm.gif?cc=1&ck=1&cl=24-bit&ds=1536x864&vl=410&ep=14806%2C4421&et=3&ja=0&ln=zh-cn&lo=0<={str(int(datetime.now().timestamp() * 1000))}&rnd=966120243&si=e92c8d65d92d534b0fc290df538b4758&su=https%3A%2F%2Fwww.tianyancha.com%2F&v=1.2.51&lv=2&sn=16695'
)
# print(a.cookies)
session.headers = headers
# 第一次请求
# 获取aliyun的cookie
resp = session.get('https://www.tianyancha.com/')
resp.encoding = 'UTF-8'
# print(resp.cookies)
# 自己添加cookie
cookie = {'ssuid': str(suid), 'bannerFlag': 'undefined'}
cookies = cookiejar_from_dict(cookie)
session.cookies.update(cookies)
params1 = {'ps': '40', '_': str(int(datetime.now().timestamp() * 1000))}
# 获取csrftoken，TYCID，undefined的cookie
resp4 = session.get(
f'https://www.tianyancha.com/user/getHomeNavHeader.html?_={str(int(datetime.now().timestamp() * 1000))}'
)
# print(resp4.cookies)
headers = {
'Host': 'hm.baidu.com',
'Connection': 'keep-alive',
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
from datetime import datetime
import json
import requests
from requests.sessions import cookiejar_from_dict
session = requests.Session()
def download(url):
return session.get(url)
if __name__ == '__main__':
url = 'https://www.tianyancha.com/'
resp = download(url)
resp.encoding = 'UTF-8'
url1 = f'https://www.tianyancha.com/claim/getLabels.json?_={int(datetime.now().timestamp() * 1000)}'
resp1 = session.get(url1)
print(resp1.text)
# uri = f'https://www.tianyancha.com/user/getHomeNavHeader.html?_={int(datetime.now().timestamp() * 1000)}'
# resp2 = session.get(uri)
cookie = {'bannerFlag': 'undefined'}
cookies = cookiejar_from_dict(cookie)
session.cookies.update(cookies)
resp3 = session.get('https://www.baidu.com')
print(resp3)
def __init__(self):
cookies = self._get_cookies()
self.session = requests.Session()
self.session.cookies = cookiejar_from_dict(cookies) # session设置cookie
'X-Requested-With': 'XMLHttpRequest',
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
'Content-Type': 'application/json; charset=UTF-8',
'Referer': 'https://www.tianyancha.com/',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.9'
}
session.get('https://www.tianyancha.com/')
session.cookies.update(
cookiejar_from_dict({
'ssuid':
'5385309444',
'bannerFlag':
'undefined',
'Hm_lpvt_e92c8d65d92d534b0fc290df538b4758':
str(int(datetime.now().timestamp() * 1000)),
'Hm_lvt_e92c8d65d92d534b0fc290df538b4758':
str(int(datetime.now().timestamp() * 1000))
}))
session.get(
f'https://www.tianyancha.com/newest.html?ps=40&_={str(int(datetime.now().timestamp() * 1000))}'
)
t1 = int(datetime.now().timestamp() * 1000)
session.get(
f'https://www.tianyancha.com/tongji/1562724106551.json?_={str(int(datetime.now().timestamp() * 1000))}'
)
# 第一次请求
import requests
from PIL import Image
from lxml import etree
from requests.sessions import cookiejar_from_dict
cookie = {}
with open('cookies.txt', 'r') as f:
result = json.load(f)
for c in result:
name = c.get('name')
value = c.get('value')
cookie[name] = value
session = requests.Session()
session.cookies = cookiejar_from_dict(cookie)
resp = session.get('https://www.tianyancha.com/search?base=bj')
print(resp.text)
html = etree.HTML(resp.text)
url_lists = html.xpath('//div[@class="result-list sv-search-container"]/div')
print(url_lists)
url = f"http://antirobot.tianyancha.com/captcha/getCaptcha.json?t={str(int(datetime.now().timestamp() * 1000))}"
data = session.get(url)
print(data.json())
bgImage = data.json().get('data').get('bgImage')
targetImage = data.json().get('data').get('targetImage')
print(base64.urlsafe_b64decode(bgImage))
