from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import selenium.webdriver.support.ui as ui
from bs4 import BeautifulSoup
import time
import json
import random
import requests
def get_cookies():
options = Options()
# options.add_argument('-headless')
driver = webdriver.Firefox(executable_path='/Users/viemaxwei/Downloads/geckodriver 2', options=options)
url = "http://www.pss-system.gov.cn/sipopublicsearch/portal/uiIndex.shtml"
driver.get(url)
time.sleep(1)
driver.find_element_by_id("j_username").send_keys("weimengxin2018")
driver.find_element_by_id("j_password_show").send_keys("adwahads6136879")
# html_login = driver.page_source
valid = input("请手动输入验证码:")
driver.find_element_by_id("j_validation_code").send_keys(valid)
driver.find_element_by_link_text("登录").click()
time.sleep(3)
cookie = driver.get_cookies()
cookie_1 = cookie[0]["name"] + "=" + cookie[0]["value"]
cookie_2 = cookie[1]["name"] + "=" + cookie[1]["value"]
cookie_3 = cookie[2]["name"] + "=" + cookie[2]["value"]
cookie_all = cookie_3 + "; " + cookie_1 + "; " + cookie_2
cookies_head = dict()
cookies_head["cookies_are"] = cookie_all
driver.quit()
return cookies_head
def requests_login_pss_system(date, pages):
res = []
result = []
# pages = 1
url = "http://www.pss-system.gov.cn/sipopublicsearch/patentsearch/showSearchResult-startWa.shtml"
head = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36',
'Connection': 'keep-alive',
'Origin': 'http://www.pss-system.gov.cn'}
# while True:
info = {"searchCondition.searchExp": "(申请日='%s') AND 公开国家/地区/组织=(HK OR MO OR TW OR (发明类型=('I' OR 'U' OR 'D') AND 公开国家/地区/组织=(CN)))" % date,
"searchCondition.executableSearchExp": "VDB:((APD='%s' AND (CC='HK' OR CC='MO' OR CC='TW' OR ((DOC_TYPE='I' OR DOC_TYPE='U' OR DOC_TYPE='D') AND CC='CN'))))" % date,
"resultPagination.start": (pages - 1) * 12,
"resultPagination.limit": 12,
"searchCondition.literatureSF": "(申请日='%s') AND 公开国家/地区/组织=(HK OR MO OR TW OR (发明类型=('I' OR 'U' OR 'D') AND 公开国家/地区/组织=(CN)))" % date}
s = requests.session()
# s.keep_alive = False
html = s.post(url, headers=head, data=info, cookies=cookies_headless).json()
time.sleep(2 + random.random() * 2.5)
page = html["searchResultDTO"]["pagination"]["totalCount"]
if page == -1:
print("page=-1,第%d页" % pages)
pages += 1
s.close()
else:
print("共%d条记录" % page)
if html["searchResultDTO"]["searchResultRecord"] != []:
for i in html["searchResultDTO"]["searchResultRecord"]:
lawStatus = i["lawStatus"]
patentType = i["patentType"]
name = i["fieldMap"]["TIVIEW"]
fnum = i["fieldMap"]["FNUM"]
cpnum = i["fieldMap"]["CPNUM"]
pnum = i["fieldMap"]["PNUM"]
VID = i["fieldMap"]["VID"]
APSN = i["fieldMap"]["APSN"]
APD = i["fieldMap"]["APD"]
PN_BAK = i["fieldMap"]["PN_BAK"]
PD = i["fieldMap"]["PD"] # 公开日
IC = i["fieldMap"]["IC"] # IPC分类号
# CPC = i["fieldMap"]["CPC"] # CPC分类号
PAVIEW = i["fieldMap"]["PAVIEW"] # 申请人
INVIEW = i["fieldMap"]["INVIEW"] # 发明人
AA = i["fieldMap"]["AA"] # 地址
AGT = i["fieldMap"]["AGT"] # 代理人
AGY = i["fieldMap"]["AGY"] # 代理机构
OWNER_STATUS = i["fieldMap"]["AGY"] # 代理机构
res.extend([lawStatus, patentType, name, fnum, cpnum, pnum, VID, APSN, APD, PN_BAK, PD, IC, PAVIEW, INVIEW, AA, AGT, AGY, OWNER_STATUS])
print(res)
middle = res.copy()
result.append(middle)
res.clear()
pages += 1
time.sleep(0.7)
s.close()
return result
else:
print("检索完毕!")
def run_fiction(date, start_page, end_page, list_con):
start = time.time()
try:
for ind in range(start_page, end_page): # 1001 1101
print("正在检索 %d 页" % ind)
test = requests_login_pss_system(date, ind)
list_con.extend(test)
if ind % 4 == 0:
print("Code冷却中。。。")
time.sleep(3 + random.random() * 7)
except:
print("完成!")
end = time.time()
print("20170101用时:%f" % (end - start))
res_10 = []
cookies_headless = get_cookies()
run = run_fiction("20170110", 240, 1501, res_10)