def __init__(self):
self.start_url = 'http://www.98pz.com/t59c11s1/1.html'
self.headers = {
'User-Agent':
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)'
}
self.r0 = Redisclient(0)
self.r1 = Redisclient(1)
self.f = FETCH()
self.m = MongoDB('mongodb://localhost', 'cuiworkdb', "98guakao_hz_qz")
def __init__(self):
self.starturl = 'http://bj.atobo.com/'
# 数据类型模板
self.data_demo = {
'_id': '',
'category_name': '',
'company_name': '',
'company_phone': '',
'company_address': ''
}
self.f = FETCH()
self.m = MongoDB(
'mongodb://10.2.1.121:17017,10.2.1.122:17017,10.2.1.123:17017',
'clues_resources', 'ZZ_20201214_rollback')
def __init__(self):
self.start_url = 'http://www.9gk.cc/zp/sichuan/'
self.headers = {
'User-Agent':
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)'
}
self.headers_fordata = {
# ":authority":"www.cbi360.net",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"Accept-Encoding":
"gzip,deflate,br",
"Accept-Language":
"zh-CN,zh;q=0.9",
"Cache-Control":
"no-cache",
"Content-Type":
"application/x-www-form-urlencoded;charset=UTF-8",
"Cookie":
"Hm_lvt_ccf8b732d64d55d0d8a73ec2bcd276ab=1612144130,1612399856,1612752316,1613704044; Hm_lpvt_ccf8b732d64d55d0d8a73ec2bcd276ab=1613704100",
"Connection":
"keep-alive",
"Host":
"www.9gk.cc",
"pragma":
"no-cache",
"Referer":
"http://www.9gk.cc/zp/p1700",
"Upgrade-Insecure-Requests":
"1",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36",
}
self.r0 = Redisclient(0)
self.r1 = Redisclient(1)
self.r2 = Redisclient(2)
self.f = FETCH()
self.m = MongoDB('mongodb://localhost', 'cuiworkdb', "9guakao_chengdu")
def __init__(self):
# 起始url
self.starturl = 'http://chengdu.atobo.com/'
# 数据类型模板
self.data_demo = {
'_id': '',
'category_name': '',
'company_name': '',
'company_phone': '',
'company_address': ''
}
# 封装的自带代理ip池的请求
self.f = FETCH()
self.m = MongoDB('mongodb://localhost', 'cuiworkdb', 'BMD_atb_chengdu')
self.r0 = Redisclient(0)
self.r1 = Redisclient(1)
self.r2 = Redisclient(2)
self.r3 = Redisclient(3)
self.category_list = []
def __init__(self):
self.start_url = 'https://b2b.11467.com/'
self.headers = b"""Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9
Accept-Language: zh-CN,zh;q=0.9
Cache-Control: no-cache
Connection: keep-alive
Cookie: Hm_lvt_819e30d55b0d1cf6f2c4563aa3c36208=1616553403,1617870200; Hm_lpvt_819e30d55b0d1cf6f2c4563aa3c36208=1617870504; arp_scroll_position=400
Host: b2b.11467.com
Pragma: no-cache
Referer: https://www.11467.com/
sec-ch-ua: "Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"
sec-ch-ua-mobile: ?0
Sec-Fetch-Dest: document
Sec-Fetch-Mode: navigate
Sec-Fetch-Site: same-site
Sec-Fetch-User: ?1
Upgrade-Insecure-Requests: 1
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36"""
self.f = FETCH()
self.m = MongoDB('mongodb://localhost', 'cuiworkdb', "shunqiwang")
self.r2 = Redisclient(2)
self.r3 = Redisclient(3)
self.area_name_list = []
def data_spdier(collection_name, periods, category, total_page, pic_url_list):
"""
:param collection_name:存入mongo的集合名 str
:param periods: 公告期数 str
:param category: 公告种类（例如送达公告，无效公告等）str
:param total_page: 公告数据总页数 int
:return: 本地cuiworkdb collection_name 中查看数据
"""
db = MongoDB('mongodb://localhost', 'cuiworkdb', collection_name)
driver = webdriver.Chrome()
driver.implicitly_wait(10)
driver.get(
'http://wsgg.sbj.cnipa.gov.cn:9080/tmann/annInfoView/annSearch.html?annNum='
)
driver.find_element_by_xpath('//input[@id="annNum"]').send_keys(periods)
# 点击公告类型
sleep(0.2)
driver.find_element_by_xpath('//select[@id="annTypes"]').click()
# 点击送达公告
#'//select[@id="annTypes"]//option[@value="TMSDGG"]'
driver.find_element_by_xpath(
'//select[@id="annTypes"]//option[@value="{}"]'.format(
category)).click()
# 点击查询
driver.find_element_by_xpath('//input[@name="annSearchBut"]').click()
sleep(2)
###
####此处代码爬取数据
###每个都是20个数据，查看需要处理
# 注册号 //table//tr[@class="evenBj"]/td[5]
# 申请人 //table//tr[@class="evenBj"]/td[6]
# 商标名称 //table//tr[@class="evenBj"]/td[7]
# 查看 //table//tr[@class="evenBj"]/td[8]
count = 0
page = 1
number = 0
while True:
# 终止页数
if page == total_page + 1:
break
sleep(1)
register_num = driver.find_elements_by_xpath(
'//table//tr[@class="evenBj"]/td[5]')
company_name = driver.find_elements_by_xpath(
'//table//tr[@class="evenBj"]/td[6]')
brand_name = driver.find_elements_by_xpath(
'//table//tr[@class="evenBj"]/td[7]')
for i in range(len(register_num)):
item = {}
item['_id'] = count + 1
item['num'] = periods
item['category'] = '送达公告'
item['type'] = ''
item['register_num'] = register_num[i].text
try:
item['company_name'] = company_name[i].text
except:
item['company_name'] = ''
try:
item['brand_name'] = brand_name[i].text
except:
item['brand_name'] = ''
if i % 2 == 0 or i == 0:
item['pic_url'] = pic_url_list[number]
print(count)
#0 1 2 3 4 5 6 7
#
else:
item['pic_url'] = pic_url_list[number - 1]
number -= 1
print(item)
db.mongo_add(item)
number += 1
count += 1
sleep(2)
driver.find_element_by_xpath(
'//div[@id="pages"]//td[8]//a//span[2]').click()
page += 1
sleep(1)
#2021/1/11 爬取商标文字信息，获取图片页码
import requests
import json
from TOOLS.mongosave import MongoDB
from TOOLS.md5encode import md5encryption
#改数据库
db = MongoDB('mongodb://localhost', 'cuiworkdb', "Shangbiao_GG-1731")
from Func.fetchJX import FETCH
s = FETCH()
#改url
url = 'http://wsgg.sbj.cnipa.gov.cn:9080/tmann/annInfoView/annSearchDG.html?O56fzBVE=5kGuYaPrUkHH9Lq8YrTHefgypngRP23L4qgXUWGQn1TKi8Yd5igEworl0xfbe_QQgAs_cOt3plSW7uuYJrq7L1WIUpjbSV_Y8jwT7pDt3qBvN3dxHlaivZlvTyYxD3JctgtaJru5MJhZZxGydeS.3ZoIfni9CZxyKko2tQuVGHLbUbVBWout9qOnP1i6mGCnxEGiUea_nSP_3xljf3U6zkgZ.c5DKXAuQiGzZjKcCLOKPsuFP3CgjXwhbt5ESmD3jfvCNBjc.Mtyy4_D_bfDngudJ.DvhsEJGWicOi6eI9.5BhuIoL5WfOPkkmcebfPQXvuh0SBxzitoPdczDRmEvxbzY2c5irpolrybljU4ZbUVkv0X8Dz5Kv38UUvuDfGXI'
#改Cookie
headers = {
"Accept": "application/json, text/javascript, */*; q=0.01",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.9",
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Content-Length": "283",
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
"Cookie":
"_gscu_1645064636=76464150vsisqf48; _gscu_2023327167=76464150m8szyi25; _trs_uv=k9wi5ba1_4030_8pj2; Hm_lvt_d7682ab43891c68a00de46e9ce5b76aa=1597140998; UM_distinctid=174ae765669480-09ef6ad0f222cb-4353761-1fa400-174ae76566aa07; goN9uW4i0iKzS=5db92.A0J2CMY23basgx2TZ.mTIJ7lkLr89FeTJ1C0aRMHE_2AokqW2_4RJ42AQplsUcWhHGBKqZ3JYJcp..cRA; __jsluid_h=b6457e19fe1b05edea1f19ada75c9f46; tmas_cookie=2272.7688.15400.0000; 018f9ebcc3834ce269=09b16dacaa2e3b985f2267dc76e5ae8f; JSESSIONID=0000mA5W99E1uXfd1qh0wgqzyqA:1bm112s99; goN9uW4i0iKzT=53cCT8DqzzR9qqqm67L0OCGfXkxa3Eg9kcZgg2BzmN4mJeGvNh.af42XRAU.5pBn6JEBVQW9X7_5Q0c0BLcubFHR3V2NtqqslXLY0Rg.3qvRoSOo.eXYEunrAawqXfJ4OYHTCLen_Z85LNWTB77aJOXfqtOqhlOUMzVD_5wlioEYc22WaLxHAvTwqbtDutolgF8kpTIldeoQJwo89qgNpe0ZOzZwHaaYC3qh7.7bucy3WpAnMVKFV_K_LPWPdL195mAzPq8uiBWY5CRMjmCfU88wyS.H5RFGSvrFx87nTLofgdhXnNMBq1vgUkTx5FYpDxvN5jaQg8eqCoedhokTjYW",
"Host": "wsgg.sbj.cnipa.gov.cn:9080",
"Origin": "http://wsgg.sbj.cnipa.gov.cn:9080",
"Pragma": "no-cache",
"Referer":
"http://wsgg.sbj.cnipa.gov.cn:9080/tmann/annInfoView/annSearch.html",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
class Spider9():
def __init__(self):
self.start_url = 'http://www.9gk.cc/zp/sichuan/'
self.headers = {
'User-Agent':
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)'
}
self.headers_fordata = {
# ":authority":"www.cbi360.net",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"Accept-Encoding":
"gzip,deflate,br",
"Accept-Language":
"zh-CN,zh;q=0.9",
"Cache-Control":
"no-cache",
"Content-Type":
"application/x-www-form-urlencoded;charset=UTF-8",
"Cookie":
"Hm_lvt_ccf8b732d64d55d0d8a73ec2bcd276ab=1612144130,1612399856,1612752316,1613704044; Hm_lpvt_ccf8b732d64d55d0d8a73ec2bcd276ab=1613704100",
"Connection":
"keep-alive",
"Host":
"www.9gk.cc",
"pragma":
"no-cache",
"Referer":
"http://www.9gk.cc/zp/p1700",
"Upgrade-Insecure-Requests":
"1",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36",
}
self.r0 = Redisclient(0)
self.r1 = Redisclient(1)
self.r2 = Redisclient(2)
self.f = FETCH()
self.m = MongoDB('mongodb://localhost', 'cuiworkdb', "9guakao_chengdu")
def get_category_url(self):
for i in range(14):
url = self.start_url + "p" + str(1700 + i)
self.r0.save_page_url("上海", url)
def get_all_page(self):
while True:
try:
url = self.r0.get_page_url("上海")
except:
break
#/page/2
self.r1.save_page_url("上海", url)
try:
html = requests.get(url=url, headers=self.headers)
except:
break
print(html.text)
res = etree.HTML(html.text)
try:
last_page = res.xpath(
'//ul[@class="pagination"]//li[@class="disable"]//following-sibling::li//a/text()'
)
if last_page == []:
last_page = list(
res.xpath('//ul[@class="pagination"]//li//a/text()')
[-1])
except Exception as e:
print(e)
break
for i in range(2, int(last_page[0]) + 1):
page_url = str(url, "utf-8") + r'/page/{}'.format(i)
self.r1.save_page_url("上海", page_url)
def parse_item_url(self):
#//div[@class="col-xs-12 boxshadow"]//div[@class="col-lg-12 bk-btm-xuxian pad-10"]//div[@class="col-lg-5 pad-left20"]//a/@href
while True:
try:
url = self.r1.get_page_url("上海")
html = requests.get(url=url, headers=self.headers)
except Exception as e:
break
# print(html.text)
res = etree.HTML(html.text)
# item_url_list = res.xpath('//div[@class="col-xs-12 boxshadow "]//div[@class="col-lg-12 bk-btm-xuxian pad-10"]//div[@class="col-lg-5 pad-left20"]//a/@href')
item_url_list = res.xpath(
'/html/body/div[5]/div/div/div/span/a/@href')
for i in range(len(item_url_list)):
print(item_url_list[i])
self.r2.save_page_url("上海", item_url_list[i])
def parse_data(self):
while True:
try:
url = self.r2.get_page_url("上海")
print(url)
except:
break
headers = self.headers_fordata
headers["Referer"] = url
html = requests.get(url=url, headers=headers)
res = etree.HTML(html.text)
try:
outName = res.xpath(
'/html/body/div[3]/div[1]/div[2]/div[4]/text()')[0]
phone = res.xpath(
'/html/body/div[3]/div[1]/div[2]/div[6]/span/text()')[0]
companyName = res.xpath(
'/html/body/div[3]/div[1]/div[1]/h2/text()')[0]
except:
continue
if is_phone(phone):
if "企业管理" not in str(companyName):
print(companyName)
item = {}
item['companyCity'] = "成都"
item['companyProvince'] = "四川省"
item['code'] = 'BUS_YT_ZZ'
item['name'] = '资质'
item['busCode'] = ''
item['webUrl'] = '无'
item['orgId'] = ''
item['deptId'] = ''
item['centreId'] = ''
item["companyName"] = companyName
item["outName"] = outName
item["resourceRemark"] = ''
item["companyTel"] = str(phone)
item["ibossNum"] = None
item['isDir'] = 0
item['isShare'] = 0
item["_id"] = md5encryption(item["companyTel"])
# item["flag"] = 0
print(item)
self.m.mongo_add(item)
else:
continue
def run(self):
self.get_category_url()
self.get_all_page()
self.parse_item_url()
self.parse_data()
def test(self):
pass
class Spider98_zhaoping:
def __init__(self):
self.start_url = 'http://www.98pz.com/t59c11s1/1.html'
self.headers = {
'User-Agent':
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)'
}
self.r0 = Redisclient(0)
self.r1 = Redisclient(1)
self.f = FETCH()
self.m = MongoDB('mongodb://localhost', 'cuiworkdb', "98guakao_hz_qz")
def parse_next_page(self):
self.r0.save_page_url(category_name='杭州求职', page_url=self.start_url)
html = requests.get(url=self.start_url, headers=self.headers)
sleep(0.5)
while True:
res = etree.HTML(html.text)
try:
next_page_url = res.xpath(
'//div[@class="pager"]//a[@class="next"]/@href')[0]
except:
break
next_page_url = 'http://www.98pz.com/' + next_page_url
print(next_page_url)
self.r0.save_page_url(category_name='杭州求职', page_url=next_page_url)
html = requests.get(url=next_page_url, headers=self.headers)
def parse_item_url(self):
while True:
url = self.r0.get_page_url(category_name='杭州求职')
try:
html = requests.get(url=url, headers=self.headers)
sleep(0.5)
except:
break
res = etree.HTML(html.text)
item_url_list = res.xpath('//td[@class="t"]//a[1]')[:-1]
for one in item_url_list:
url = one.xpath('./@href')[0]
self.r1.save_item_url(category_name='杭州求职', url=url)
def parse_data(self):
while True:
item = {}
url = self.r1.get_item_url(category_name='杭州求职')
if b'www' not in url:
url = 'http://www.98pz.com' + str(url)
try:
html = requests.get(url=url, headers=self.headers)
sleep(0.5)
except Exception as e:
print(e)
continue
res = etree.HTML(html.text)
try:
company_name = res.xpath(
'//span[@class="firm-name"]/a/@title')[0]
except:
continue
# try:
# info = res.xpath('//li/i[contains(text(),"注册情况：")]/following-sibling::*/text()')[0]
# print(info)
# except:
# continue
contact_people = res.xpath(
'//li/i[contains(text(),"联 系 人：")]/following-sibling::*/text()'
)[0]
print(contact_people)
try:
phone_url = res.xpath(
'//li/i[contains(text(),"固定电话：")]/following-sibling::*//img/@src'
)[0]
except:
try:
phone_url = res.xpath(
'//li/i[contains(text(),"手机号码：")]/following-sibling::*//img/@src'
)[0]
except:
continue
resourceMark = res.xpath(
'//li/i[contains(text(),"职位类型：")]/following-sibling::a//text()'
)
resourceMark = resourceMark[0] + resourceMark[1]
if phone_url == '':
phone = ''
else:
try:
phone = self.rec_img(phone_url)
except:
continue
item['companyCity'] = '杭州'
item['companyProvince'] = '浙江省'
item['code'] = 'BUS_YT_ZZ'
item['name'] = '资质'
item['busCode'] = ''
item['webUrl'] = '无'
item['orgId'] = ''
item['deptId'] = ''
item['centreId'] = ''
item["companyName"] = company_name
item["outName"] = contact_people
item["resourceRemark"] = resourceMark
item["companyTel"] = phone
item["ibossNum"] = None
item['isDir'] = 0
item['isShare'] = 0
item["_id"] = md5encryption(item["companyTel"])
print(item)
self.m.mongo_add(item)
def rec_img(self, img_url):
url_b = img_url.split('data:image/gif;base64,')[1]
url_b = url_b.encode()
content = base64.b64decode(url_b)
with open(r'G:\rec_pic\target.jpg', 'wb') as f:
f.write(content)
text = pytesseract.image_to_string(
Image.open(r'G:\rec_pic\target.jpg').convert('RGB'))
os.remove(r'G:\rec_pic\target.jpg')
return text
def test(self):
self.parse_item_url()
def run(self):
self.parse_next_page()
self.parse_item_url()
self.parse_data()
class Atb_spider():
def __init__(self):
self.starturl = 'http://bj.atobo.com/'
# 数据类型模板
self.data_demo = {
'_id': '',
'category_name': '',
'company_name': '',
'company_phone': '',
'company_address': ''
}
self.f = FETCH()
self.m = MongoDB(
'mongodb://10.2.1.121:17017,10.2.1.122:17017,10.2.1.123:17017',
'clues_resources', 'ZZ_20201214_rollback')
def get_html(self, url):
html = self.f.fetch(url)
return html
def parse_category_html(self, html):
# 解析种类页面获取种类名称和种类url
response = etree.HTML(html)
category_list = response.xpath(
'//div[@class="sidebar-category"]/ul//li/p[@class="pcategory_son"]/a'
)
for category in category_list:
category_name = category.xpath('./text()').get()
category_url = category.xpath('./@href').get()
category_url = 'http:' + category_url
# yield category_url
yield self.parse_more_html(self.get_html(category_url),
category_name=category_name)
def parse_more_html(self, html, category_name):
# 获取更多页选项的url
response = etree.HTML(html)
more_company_url = response.xpath(
'//div[@class="product-list-more"]/a/@href').get()
yield self.parse_allpage(self.get_html(more_company_url),
category_name=category_name)
def parse_allpage(self, html, category_name):
# 获取所有翻页url
# 调用parse_one_url解析每个企业url yield出去，一页结束进入下方代码解析下一页url，再解析每个企业url
self.parse_one_url(html, category_name=category_name)
response = etree.HTML(html)
one_page_url = response.xpath(
'//a[contains(text(),"下一页")]/@href').extract()
if one_page_url:
one_page_url = 'http://www.atobo.com' + one_page_url[0]
if one_page_url != 'http://www.atobo.com#':
yield self.parse_allpage(self.get_html(one_page_url),
category_name=category_name)
def parse_one_url(self, html, category_name):
# 获取一页当中每个企业的url list
response = etree.HTML(html)
one_url_list = response.xpath(
'//li[@class="product_box"]//li[@class="pp_name"]//a[@class="CompanyName"]/@href'
).extract()
for one_url in one_url_list:
one_url = "http://www.atobo.com/" + one_url
yield self.parse_data(self.get_html(one_url),
category_name=category_name)
def parse_data(self, html, category_name):
# 获取最终数据
response = etree.HTML(html)
try:
# 图片规则
company_name = response.xpath(
'//div[@class="company-intro"]//tr[1]/td/text()').get()
company_address = response.xpath(
'//div[@class="company-intro"]//table//tr[2]').get()
company_address = find_address(company_address)
if not company_name:
# 非图片规则
company_name = response.xpath(
'//div[@class="company-banner"]//p[@class="t-companyname"]/text()'
).get()
company_address = response.xpath(
'//div[@class="card-context"]//ul[2]//li[2]').get()
company_address = find_address(company_address)
except Exception:
company_name = None
company_address = None
try:
# 有手机号的情况
company_phone = response.xpath(
'//div[@class="company-intro"]//tr/td/img/@src').extract()[1]
company_phone = 'http:' + company_phone
phone2 = get_phone(picurl=company_phone)
phone = ''.join(phone2)
if not company_phone:
phone1 = response.xpath('//ul[4]//li[2]').get()
pattern = re.compile("\d+", re.S)
phone = pattern.findall(phone1)
if not phone:
phone3 = response.xpath(
'//div[@class="company-intro"]//tr/td/img/@src'
).extract()[0]
try:
phone4 = 'http:' + phone3
phone5 = get_phone(picurl=phone4)
phone = ''.join(phone5)
except:
phone4 = 'http:' + phone3
phone5 = get_phone(picurl=phone4)
phone = phone5[0]
except Exception:
phone = None
if company_name and phone:
# mongo储存数据
id = phone_encrypte(phone)
data = self.data_demo
data["_id"] = id
data["categoryname"] = category_name
data["companyname"] = company_name
data["companyaddress"] = company_address
data["companyphone"] = phone
self.m.save_data(datadict=data)
yield
def runspider(self):
html = self.get_html(self.starturl)
self.parse_category_html(html)
#白名单通用api
#每日BMD任务更改日期（mongo集合名和文件位置）
from TOOLS.mongosave import MongoDB
db = MongoDB('mongodb://localhost', 'cuiworkdb', 'BMD20210205-chengdu')
Format_code = {
"项目": "BUS_YT_XM",
"创业发展": "BUS_YT_CY",
"资质": "BUS_YT_ZZ",
"互联网": "BUS_YT_HLW",
"财税": "BUS_YT_CS",
"会计": "BUS_YT_KJ",
"金融发展": "BUS_YT_JRFZ",
"法律": "BUS_YT_FL",
"培训（大卓商学院）": "BUS_YT_DZSXY",
"综合": "BUS_YT_ZH",
"项目(知产)": "BUS_YT_ZSCQ",
"品牌": "BUS_YT_PP",
"人事外包": "BUS_YT_RSWB",
"装饰": "BUS_YT_ZS",
"融资": "BUS_YT_DK",
"商标版权": "BUS_YT_SBBQ",
"专利项目": "BUS_YT_ZLXM",
"巨方地产(禁用)": "BUS_YT_JFDC",
"认证": "BUS_YT_TXRZ",
"创新": "BUS_YT_CX",
"网点交易": "BUS_YT_WDJY"
}
city = {
#图片下载到“下载”文件夹，按照数字顺序重命名
from selenium import webdriver
from time import sleep
from selenium.webdriver import ActionChains
from TOOLS.mongosave import MongoDB
import os
from pykeyboard import *
from pymouse import *
###固定代码
k = PyKeyboard()
m = PyMouse()
db = MongoDB('mongodb://localhost', 'cuiworkdb', 'Shangbiao_GG')
driver = webdriver.Chrome()
driver.maximize_window()
driver.implicitly_wait(10)
driver.get(
'http://wsgg.sbj.cnipa.gov.cn:9080/tmann/annInfoView/annSearch.html?annNum='
)
num = '1677'
# 输入期数（可更改）
driver.find_element_by_xpath('//input[@id="annNum"]').send_keys(num)
# 点击公告类型