def meizu():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://mwx-api.meizu.com/metter-price/get-cat'
url2 = 'https://mwx-api.meizu.com/metter-price/get-metter'
try:
js1 = hhnetworm.getRes(url1, result='j')
for aa in js1['data']:
js2 = hhnetworm.getRes(url2,
data={'mobile_cat': {aa['id']}},
result='j')
for bb in js2['data']:
price = int(float(bb['price']))
dic = {
'business': '官修',
'brand': '魅族',
'type': '手机',
'model': aa['name'],
'color': '',
'malfunction': bb['repair_name'],
'plan': '',
'price': price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='魅族', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('魅族'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def xiaomi():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://www.mi.com/service/materialprice/'
try:
sel1 = hhnetworm.getRes(url1, result='t-s')
text = sel1.css("body script:nth-child(3)").extract_first()
js1 = json.loads(text[text.find("=") + 1:text.find("</script>")])
for aa in js1:
for bb in aa['child']:
if 'child' in bb.keys():
try:
for cc in bb['child']: rt_arr.append(dicMaker(cc))
except:
for cc in bb['child']:
for dd in cc['child']: rt_arr.append(dicMaker(dd))
else:
try:
rt_arr.append(dicMaker(bb))
except:
print(bb['child'])
HhTime.costPrinter(st_time, pjName='小米', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('小米'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def vivo():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://www.vivo.com.cn/service/accessory/product/list'
url2 = "http://www.vivo.com.cn/service/accessory/query"
try:
js1 = hhnetworm.getRes(url1, method='p', result='j')
for aa in js1['data']:
for bb in aa['products']:
js2 = hhnetworm.getRes(url2,
method='p',
data={'productId': bb['id']},
result='j')
for cc in js2['data']:
price = int(float(str(cc['price'])))
dic = {
'business': '官修',
'brand': 'vivo',
'type': '手机',
'model': bb['name'],
'color': '',
'malfunction': cc['name'],
'plan': '',
'price': price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='vivo', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('vivo'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def haoyun56():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://www.haoyun56.com/xue/chepaihao/'
try:
sel1 = hhnetworm.getRes(url1)
for aa in sel1.css("#dlProvince tr td div a"):
pro = aa.css("::text").extract_first().strip()
sel2 = hhnetworm.getRes(url1 + "?province={}".format(
aa.css("::attr(href)").extract_first()[-6:]))
for bb in sel2.css("#div_Provice table tr:nth-child(n+2)"):
dic = {
'source':
'haoyun56',
"province":
pro,
"city":
bb.css("td:nth-child(2) a::text").extract_first().strip(),
"code":
bb.css("td:nth-child(3)::text").extract_first().strip()
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='haoyun56')
finish = True
except:
print("----------Wrong: {}".format('haoyun56'))
traceback.print_exc()
finally:
return dlData_haoyun56(rt_arr) if finish else []
def shunfeng():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = "http://www.sf-express.com/sf-service-owf-web/service/region/A000086000/subRegions"
url2 = "http://www.sf-express.com/sf-service-owf-web/service/region/%s/subRegions"
try:
js1 = hhnetworm.getRes(url1, data={'lang': 'sc'}, result='j')
for aa in js1:
province = aa['name']
js2 = hhnetworm.getRes(url2 % str(aa['code']), data={'level': 2, 'lang': 'sc'}, result='j')
for bb in js2:
city = bb['name']
if str(bb['level']).strip() == "4":
dic = {'province': province, 'city': city, 'district': ''}
rt_arr.append(dic)
print(dic)
else:
js3 = hhnetworm.getRes(url2 % str(bb['code']), data={'level': 3, 'lang': 'sc', 'region': 'cn'}, result='j')
for cc in js3:
dic = {'province': province, 'city': city, 'district': cc['name']}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='顺丰地址库', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('顺丰地址库'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def tcmap():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = "http://www.tcmap.com.cn/list/car_list.html"
try:
# 除 上海 海南 重庆 新疆 青海
sel1 = hhnetworm.getRes(url1)
for aa in sel1.css("#list360 table"):
pro = aa.css("tr:nth-child(1) td:nth-child(1) strong a::text"
).extract_first()
for bb in aa.css("tr:nth-child(n+2)"):
dic = {
'source': 'tcmap',
"province": pro,
"city": bb.css("td:nth-child(1) a::text").extract_first(),
"code": bb.css("td:nth-child(2)::text").extract_first()
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='tcmap')
finish = True
except:
print("----------Wrong: {}".format('tcmap'))
traceback.print_exc()
finally:
return dlData_tcmap(rt_arr) if finish else []
def haocc():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
try:
sel1 = hhnetworm.getRes("http://www.51hao.cc/")
for i, aa in enumerate(sel1.css("div.fkt:nth-child(n+3)"), 1):
province = aa.css("div.fkbj p a::text").extract_first().replace(
" ", "")
print("{0} :{1}".format(i, province))
for url, city in zip(
aa.css("div.fklk p a::attr(href)").extract(),
aa.css("div.fklk p a::text").extract()):
sel2 = hhnetworm.getRes(url)
for bb in sel2.css("div.all ul:nth-child(n+2)"):
for number in bb.css("li a::text").extract():
number = str(number).replace(" ", "")
if len(number) == 7:
dic = {
'province': province,
'city': city.replace(" ", ""),
'number': number
}
rt_arr.append(dic)
print(dic)
else:
print("错误号码 :", number)
HhTime.costPrinter(st_time, pjName='手机号码归属地')
finish = True
except:
print("----------Wrong: {}".format('手机号码归属地'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def jinli():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://www.gionee.com/id-478_op-productPart.shtml'
url2 = 'https://www.gionee.com/'
wrong_arr = ['one', '智能机']
try:
sel1 = hhnetworm.getRes(url1)
for aa in sel1.css(".xl_phone a"):
sel2 = hhnetworm.getRes(url2 +
aa.css("::attr('href')").extract_first())
for bb in sel2.css(".peijian_list li"):
sel3 = hhnetworm.getRes(
url2 + bb.css("bt a::attr('href')").extract_first())
for cc in sel3.xpath(
"//table[@class='MsoNormalTable']/tbody/tr[position()>2 and position()<last()]"
):
price = str(
cc.css("td:nth-child(2) p span span::text").
extract_first()).strip() if cc.css(
"td:nth-child(2) p span span::text").extract_first(
) else str(
cc.css("td:nth-child(2) p span::text").
extract_first())[1:].strip()
price = price.strip().replace('￥', '').replace(',', '')
if price and price not in wrong_arr:
dic = {
'business':
'官修',
'brand':
'金立',
'type':
'手机',
'model':
bb.css("bt a::text").extract_first(),
'color':
'',
'malfunction':
str(
cc.css("td:nth-child(1) p span::text").
extract_first()).strip(),
'plan':
'',
'price':
price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='金立', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('金立'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def baidu_search(wordArr, need_secondNet_title=False):
st_time, rt_arr, finish = time.time(), [], False
url1 = 'https://www.baidu.com/s'
try:
for word in wordArr:
hhnetworm = HhNetworm()
data1 = {'word': word,
'tn': '88093251_hao_pg', # 定参 + 必传
# 'ie': 'utf-8', # 定参 + 可不传
# 'srcqid': '2239491606901131802', # 定参 + 可不传
# 'sc': 'UWY3rj04n1cdnNqCmyqxTAThIjYkPHnzPj6snW0kPWbdFhnqpA7EnHc1Fh7W5Hn1PWDkPjbYPs' # 定参 + 可不传
}
sel1 = hhnetworm.getRes(url1, data=data1, verify=False)
for aa in sel1.css("#content_left div.result.c-container"):
title_1 = aa.css("h3 a:nth-child(1) em::text").extract()
title_2 = aa.css("h3 a:nth-child(1)::text").extract()
brief_1 = aa.css("div.c-abstract em::text").extract()
brief_2 = aa.css("div.c-abstract::text").extract()
href = aa.css("h3 a:nth-child(1)::attr(href)").extract_first() # 网址
title = help_func_baidu(title_1, title_2) # 标题
brief = help_func_baidu(brief_1, brief_2) # 简介
dic = {
'word': word, # 检索词
'title': title, # 标题
'brief': brief, # 简介
'href': href # 网址
}
if need_secondNet_title:
sel2 = hhnetworm.getRes(href)
secondNet_title = sel2.css("head title::text").extract_first() # 二级连接标题
dic['secondNet_title'] = secondNet_title
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='模拟百度搜索')
finish = True
except:
print("----------Wrong: {}".format('模拟百度搜索'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def samsung(model_arr):
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = "http://support-cn.samsung.com/supportcn/support/material_price/GetCailAjax.aspx"
url2 = 'http://support-cn.samsung.com/supportcn/support/material_price/default.aspx'
try:
js1 = hhnetworm.getRes(url1, data={'pid': 1}, result='j')
for model in model_arr:
for aa in js1['Items']:
sel1 = hhnetworm.getRes(url2,
method='p',
data={
'__EVENTTARGET': '',
'btnSearch': '提交',
'ddlCail': aa['PName'],
'ddlProduct': 1,
'txtModel': model
})
mal_arr, price_arr = [], [] # 故障,价格
for bb in sel1.css(
"div.table_box:nth-child(4) table:nth-child(1) tr:nth-child(n+2)"
):
price = int(
bb.css(
"td:nth-child(2)::text").extract_first().strip())
malfunction = bb.css(
"td:nth-child(1)::text").extract_first().strip()
malfunction = malfunction[malfunction.find(' ') + 1:]
mal_arr.append(malfunction), price_arr.append(price)
# 辅料价格
help_price = sum([
price_arr[index] for index, bb in enumerate(mal_arr)
if bb.find('辅料') != -1
])
for index, bb in enumerate(mal_arr):
if bb.find('辅料') == -1:
dic = {
'business': '官修',
'brand': '三星',
'type': '手机',
'model': model,
'color': '',
'malfunction': bb,
'plan': '',
'price': price_arr[index] + help_price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='三星', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('三星'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def jikexiu():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://www.jikexiu.com/common/brands.json'
url2 = 'https://www.jikexiu.com/order/selSolution'
url3 = 'https://www.jikexiu.com/order/getDeviceAttributeList.json'
url4 = 'https://www.jikexiu.com/order/getDeviceSolution.json'
url5 = 'https://www.jikexiu.com/order/getSolutionMalfunction.json'
try:
js1 = hhnetworm.getRes(url1, method='p', result='j')
for aa in js1['brandList']:
sel2 = hhnetworm.getRes(url2, data={'brandId': aa['id'], 'categoryId': 12})
for bb in sel2.css("#selectDevice ul li"):
color = ''
attributeId, color_id = '', ''
js3 = hhnetworm.getRes(url3, method='p', result='j', data={'deviceId': bb.css("::attr(deviceid)").extract_first()})
for cc in js3['deviceAttributeList']:
color += cc['attributeValue'] + "," # 颜色
attributeId, color_id = cc['attributeId'], cc['id']
js4 = hhnetworm.getRes(url4, method='p', result='j', data={'attrs[0].attributeId': attributeId, 'attrs[0].valueId': color_id,
'deviceId': bb.css("::attr(deviceid)").extract_first()})
for dd in js4['malfunctionList']:
js5 = hhnetworm.getRes(url5, method='p', result='j', data={'attrs[0].attributeId': attributeId, 'attrs[0].valueId': color_id,
'deviceId': bb.css("::attr(deviceid)").extract_first(),
'malfunctionId': dd['id']})
for ee in js5['solutionMalfunctionList']:
dic = {
'business': '极客修',
'brand': aa['name'],
'type': '手机',
'model': bb.css("::text").extract_first(),
'color': color[:-1],
'malfunction': dd['name'],
'plan': ee['method'],
'price': ee['price'],
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='极客修', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('极客修'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def huawei():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://consumer.huawei.com/support/services/service/parts/product/list'
url2 = 'http://consumer.huawei.com/support/services/service/parts/list'
wrong_arr = ['None']
try:
js1 = hhnetworm.getRes(url1,
result='j',
data={
'json':
'jQuery111308920180139684155_1508484428667',
'productId': 4903,
'_': 1508484428671,
'siteCode': 'cn'
})
for aa in js1:
js2 = hhnetworm.getRes(
url2,
result='j',
data={
'json': 'jQuery111308920180139684155_1508484428667',
'productCode': aa['productCode'],
'_': 1508484428672,
'siteCode': 'cn'
})
for bb in js2:
price = str(bb['price']).replace("￥", '')
if price not in wrong_arr:
dic = {
'business': '官修',
'brand': '华为',
'type': '手机',
'model': aa['productTypeName'],
'color': '',
'malfunction': bb['partsType'],
'plan': '',
'price': price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='华为', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('华为'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def hiweixiu():
st_time, n, rt_arr, finish, hhnetworm = time.time(
), 0, [], False, HhNetworm()
url1 = 'https://www.hiweixiu.com/step/selectInfo'
url2 = 'https://www.hiweixiu.com/step/getMouldlistsByBrandid'
url3 = 'https://www.hiweixiu.com/step/detailInfo'
try:
sel1 = hhnetworm.getRes(url1)
for aa in sel1.css("div.brand_list ul li"):
brand = aa.css("a::text").extract_first().strip()
js2 = hhnetworm.getRes(
url2,
result='j',
data={'brand_id': aa.css("::attr(data-id)").extract_first()
})['data']['mould']
for key in js2.keys():
for bb in js2[key]:
sel3 = hhnetworm.getRes(url3, data={'mid': bb['MouldId']})
rp_info = json.loads(
sel3.css("input.rp_info::attr(value)").extract_first())
for cc in rp_info.keys():
for dd in rp_info[cc].keys():
for ee in rp_info[cc][dd].keys():
data = rp_info[cc][dd][ee]
dic = {
'business': 'Hi维修',
'brand': brand,
'type': bb['ProductName'],
'model': bb['MouldName'],
'color':
data['ColorName'].replace("/", ","),
'malfunction':
data['faulttype_detail_name'],
'plan': data['RepairType'],
'price': data['Price'],
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='Hi维修', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('Hi维修'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def maoyan100():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://maoyan.com/board/4'
try:
for offset in range(0, 100, 10):
sel1 = hhnetworm.getRes(url1, data={'offset': offset})
for aa in sel1.css("#app div div div.main dl dd:nth-child(n+1)"):
actors = aa.css("p.star::text").extract_first()
year = aa.css("p.releasetime::text").extract_first()
year = year[year.find('：') + 1:]
dic = {
'source':
'猫眼', # 商家
"name":
aa.css("a::attr(title)").extract_first(), # 名称
"sorce":
float(
aa.css("i.integer::text").extract_first() +
aa.css("i.fraction::text").extract_first()), # 评分
"type":
'', # 类型
"country":
year[year.find('(') +
1:year.find(')')] if year.find('(') != -1
and year.find(')') != -1 else '', # 国家
"year":
year[:year.find('(')] if year.find('(') != -1
and year.find(')') != -1 else year, # 年份
"director":
'', # 导演
"actors":
actors[actors.find('：') + 1:].strip(), # 主演
"pictureUrl":
aa.css("a img::attr(data-src)").extract_first(), # 图片url
'have_watched':
'N' # 是否观看过
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='猫眼100', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('猫眼100'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def shanxiuxia():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://api.shanxiuxia.com/api/PhoneType/brand'
url2 = 'http://api.shanxiuxia.com/api/PhoneType/brandPhone'
url3 = 'http://api.shanxiuxia.com/api/PhoneType/malclass'
url4 = 'http://api.shanxiuxia.com/api/PhoneType/maldetails'
try:
js1 = hhnetworm.getRes(url1, method='p', result='j')
js2 = hhnetworm.getRes(url2, method='p', result='j')
for aa in js2['data']:
js3 = hhnetworm.getRes(url3,
method='p',
result='j',
data={'id': aa['id']})
for bb in js3['data']['malfunction']:
js4 = hhnetworm.getRes(url4,
method='p',
result='j',
data={
'id': aa['id'],
'type_id': bb['id']
})
for cc in js4['data']:
for dd in js1['data']:
if aa['brand_id'] == dd['id']:
dic = {
'business': '闪修侠',
'brand': dd['name'],
'type': aa['category'],
'model': aa['name'],
'color': aa['color'],
'malfunction': cc['malfunction'],
'plan': '',
'price': cc['price_reference'],
}
rt_arr.append(dic)
print(dic)
break
HhTime.costPrinter(st_time, pjName='闪修侠', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('闪修侠'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def tcl():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://wechat-api.tclsfdj.com:88/ha-wechat/v1/repair/brands'
url2 = 'http://wechat-api.tclsfdj.com:88/ha-wechat/v1/repair/models/%s'
url3 = 'http://wechat-api.tclsfdj.com:88/ha-wechat/v1/repair/colours/%s'
url4 = 'http://wechat-api.tclsfdj.com:88/ha-wechat/v1/repair/material/%s'
url5 = 'http://wechat-api.tclsfdj.com:88/ha-wechat/v1/repair/fault/%s'
try:
js1 = hhnetworm.getRes(url1, method='p', result='j')
for aa in js1['data']:
if aa['brandName'] != '其它':
js2 = hhnetworm.getRes(url2 % aa['brandId'], result='j')
for bb in js2['data']:
color = ''
js3 = hhnetworm.getRes(url3 % bb['modelId'], method='p', result='j')
for each in js3['data']:
color += each['colourName'] + ","
js4 = hhnetworm.getRes(url4 % js3['data'][0]['colourId'], method='p', result='j')
for cc in js4['data']:
js5 = hhnetworm.getRes(url5 % bb['modelId'], method='p', result='j')
for dd in js5['data']['faultInfo']:
if cc['faultId'] == dd['faultId']:
dic = {
'business': 'TCL',
'brand': aa['brandName'],
'type': '手机',
'model': bb['mobileName'],
'color': color[:-1],
'malfunction': dd['faultName'],
'plan': dd['faultPlan'],
'price': cc['price'],
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='tcl', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('tcl'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def mashangxiu():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://www.mashangxiu.com/repair/repair'
url2 = 'https://www.mashangxiu.com/device/acquireDeviceByBrandName'
url3 = 'https://www.mashangxiu.com/device/acquireDeviceByBrandAndModel'
try:
sel1 = hhnetworm.getRes(url1)
for aa in sel1.css(".mobileNav ul li a::attr('id')").extract():
js2 = hhnetworm.getRes(url2,
result='j',
data={
'needColor': 'Y',
'productBrand': aa
})
for bb in js2['modelList']:
js3 = hhnetworm.getRes(url3,
result='j',
data={
'needColor': 'Y',
'productBrand': aa,
'productModel': bb
})
for cc in js3['materialTypeList']:
dic = {
'business': '马上修',
'brand': aa,
'type': '手机',
'model': bb,
'color': '',
'malfunction': cc['materialName'],
'plan': '',
'price': cc['outerFee'],
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='马上修', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('马上修'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def apple():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://support.apple.com/zh-cn/iphone/repair/service/pricing'
try:
sel1 = hhnetworm.getRes(url1)
for aa in sel1.css(
"#faq-regular div:nth-child(4) #tableWraper table tr:nth-child(n+2)"
):
model = ''
for bb in aa.css("td:nth-child(1)::text").extract():
model += bb.strip()
price = HhBase.toInt(
aa.css("td:nth-child(2)::text").extract_first().replace(
"RMB ", "").replace(",", ""))
if not price:
price = HhBase.toInt(
aa.css("td:nth-child(3)::text").extract_first().replace(
"RMB ", "").replace(",", ""))
for bb in model.split('、'):
dic = {
'business': '官修',
'brand': '苹果',
'type': '手机',
'model': bb,
'color': '',
'malfunction': '内屏',
'plan': '',
'price': price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='苹果', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('苹果'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def oppo():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'https://www.oppo.com/cn/service/part'
url2 = 'https://www.oppo.com/cn/service/productlist'
wrong_arr = [' ']
try:
sel1 = hhnetworm.getRes(url1)
for model in sel1.css(
"#part-select div.select-dropdown ul li span::text").extract():
js2 = hhnetworm.getRes(url2,
data={
'isapp': 0,
'mobile': model
},
result='j')
sel2 = Selector(js2['data'])
for name, price in zip(
sel2.css("div.part-list-name span::text").extract(),
sel2.css("div.part-list-price::text").extract()[1:]):
if price not in wrong_arr:
price = int(float(price.strip().replace('¥', '')))
dic = {
'business': '官修',
'brand': 'oppo',
'type': '手机',
'model': model,
'color': '',
'malfunction': name,
'plan': '',
'price': price,
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='oppo', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('oppo'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def douban250():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = "https://movie.douban.com/top250?start=%d&filter="
try:
for myindex in range(10):
sel = hhnetworm.getRes(url1 % (myindex * 25))
for zzz in sel.css(
"#content div div.article ol.grid_view li div.item"):
for aa in zzz.css("div.info"):
name = ""
for bb in aa.css("div.hd a span"):
name += bb.css("::text").extract_first()
body = aa.css("div.bd p:nth-child(1)::text").extract()
introduction1 = body[0].replace(" ", "").replace(" ", "")
introduction2 = body[1].replace(" ", "").replace(" ", "")
director = introduction1[introduction1.find("导演:") +
len("导演:"):introduction1.
find("主演:")].replace("'",
"~") # 导演
actors = introduction1[introduction1.find("主演:") +
len("主演:"):].replace("'", "~") # 主演
year = int(introduction2[:introduction2.find("/")].replace(
"\n", "")[:4]) # 年份
introduction2 = introduction2[introduction2.find("/") + 1:]
country = introduction2[:introduction2.find("/")].replace(
" ", "").replace(" ", "") # 国家
introduction2 = introduction2[introduction2.find("/") + 1:]
dic = {
'source':
'豆瓣', # 商家
"name":
name.replace(" ", "").replace(" ",
"").replace("'",
"~"), # 名称
"sorce":
float(
aa.css("div.bd div span.rating_num::text").
extract_first()), # 评分
"type":
introduction2[:introduction2.find("/")].replace(
" ", "").replace(" ", ""), # 类型
"country":
country, # 国家
"year":
year, # 年份
"director":
director, # 导演
"actors":
actors, # 主演
"pictureUrl":
zzz.css("div.pic a img::attr(src)").extract_first(
), # 图片url
'have_watched':
'N' # 是否观看过
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='豆瓣250', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('豆瓣250'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def jihouhou():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = 'http://www.hohofast.com/api/web/order/create'
url2 = "http://www.hohofast.com/api/web/brand/list"
url3 = "http://www.hohofast.com/api/web/model/list"
url4 = "http://www.hohofast.com/api/web/model/submit"
url5 = "http://www.hohofast.com/api/web/order/other"
url6 = "http://www.hohofast.com/api/web/order/otherSubmit"
url7 = "http://www.hohofast.com/api/web/brief/appraisement/data"
try:
sel1 = hhnetworm.getRes(url1, method='p')
for aa in sel1.css("#select_brand div"):
brand_id = aa.css("::attr(data-brand)").extract_first()
js2 = hhnetworm.getRes(url2,
method='p',
data={'uuid': brand_id},
result='j')
for bb in js2['items']:
js3 = hhnetworm.getRes(url3,
data={
'type': brand_id,
'uuid': bb['uuid']
},
result='j')
for cc in js3['items']:
color, color_id = '', ''
for dd in json.loads(cc['info'])['colors']:
color += dd['color'] + "," # 颜色
color_id = dd['uuid']
hhnetworm.getRes(url4,
method='p',
data={
'type': brand_id,
'bUuid': bb['uuid'],
'mUuid': cc['uuid'],
'color': color_id
})
sel5 = hhnetworm.getRes(url5)
for ee in sel5.css(
"#select_part div.item.malfunction-item"):
hhnetworm.getRes(
url6,
method='p',
data={
'part':
ee.css("::attr(data-part)").extract_first(),
'service': 1
})
js7 = hhnetworm.getRes(url7, result='j')
js7 = js7['data']['commonTechItems']
if js7:
dic = {
'business':
'极吼吼',
'brand':
aa.css("::attr(data-name)").extract_first(),
'type':
bb['name'],
'model':
cc['name'],
'color':
color[:-1],
'malfunction':
ee.css("h5::text").extract_first(),
'plan':
js7[0]['solution']['showname'],
'price':
js7[0]['price'],
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='极吼吼', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('极吼吼'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def wuyixiu():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url2 = 'http://www.51xiu.cc/fi/choosePlans'
url3 = 'http://www.51xiu.cc/fi/select'
url4 = 'http://www.51xiu.cc/fi/getPlan'
try:
sel1 = hhnetworm.getRes('http://www.51xiu.cc/repair')
for aa in sel1.css("div.big-box div div:nth-child(2) div div"):
bId = aa.css("::attr('brandid')").extract_first().strip()
tId = aa.css("::attr('tid')").extract_first().strip()
js2 = hhnetworm.getRes(url2,
method='p',
data={
'bId': bId,
'tId': tId
},
result='j')
for bb in js2['versionList']:
versionName = bb['versionName'] # 型号
color, cId = '', ''
text3 = hhnetworm.getRes(url3,
data={
'bId': bId,
'tId': tId,
'versionName': versionName,
'versionId': bb['id']
},
result='t')
for index, each in enumerate(
BeautifulSoup(text3, 'lxml').find('div',
class_='clear')):
if index % 2:
color += each.text + ','
cId = each['colorid']
js4 = hhnetworm.getRes(url4,
method='p',
result='j',
data={'cId': cId})
for cc in js4['result']:
dic = {
'business': '51修',
'brand': aa.css("::text").extract_first().strip(),
'type': '手机',
'model': versionName,
'color': color[:-1],
'malfunction': cc['detail'],
'plan': cc['plan'],
'price': cc['price'],
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='51修', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('51修'))
traceback.print_exc()
finally:
return dl_wuyixiu_data(rt_arr) if finish else []
def tcmap():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = "http://www.tcmap.com.cn/list/daima_list.html"
con_url = "http://www.tcmap.com.cn"
try:
sel = hhnetworm.getRes(url1)
for i, aa in enumerate(sel.css("#list360"), 1):
province = aa.css("strong a::text").extract_first().replace(
" ", "") # 省
print("{0} :{1}".format(i, province))
sel = hhnetworm.getRes(
con_url + aa.css("strong a::attr(href)").extract_first())
for bb in sel.css(
"#page_left table:nth-child(5) tr:nth-child(n+2)"):
for cc in bb.css("td:nth-child(6) a::attr(href)").extract():
res = requests.get(con_url + str(cc)).content
# 编码匹配
sel = False
try:
sel = Selector(res.decode("gb18030"))
except:
try:
sel = Selector(res.decode("utf-8"))
except:
print("decode all failed!")
if sel:
for dd in sel.css(
"#page_left div:nth-child(4) div:nth-child(2) table"
):
dic = {
'province':
province, # 省
'id1':
aa.css("::text").extract_first().replace(
" ", ""), # 身份证编号1
'city':
bb.css("td strong a::text").extract_first().
replace(" ", ""), # 市
'id2':
bb.css("td:nth-child(5)::text").extract_first(
).replace(" ", ""), # 身份证编号2
'district':
dd.css("tr:nth-child(1) td:nth-child(1)::text"
).extract_first().replace(" ",
"")[1:], # 区
'id3':
dd.css("tr:nth-child(2) td:nth-child(2)::text"
).extract_first().replace(
" ", "")[1:], # 身份证编号3
'phoneAreaCode':
bb.css("td:nth-child(4)::text").extract_first(
).replace(" ", ""), # 电话区号
'postCode':
dd.css("tr:nth-child(3) td:nth-child(2)::text"
).extract_first().replace(
" ", "")[1:], # 邮政编码
'carCode':
dd.css("tr:nth-child(4) td:nth-child(1)::text"
).extract_first().replace(" ",
"")[1:], # 车牌
'population':
check_1(
dd.css(
"tr:nth-child(5) td:nth-child(1)::text"
).extract_first()), # 人口
's_area':
check_1(
dd.css("tr:nth-child(6) td::text").
extract_first()) # 区域面积
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='身份证户籍编号')
finish = True
except:
print("----------Wrong: {}".format('身份证户籍编号'))
traceback.print_exc()
finally:
return rt_arr if finish else []
def jingdong():
st_time, rt_arr, finish, hhnetworm = time.time(), [], False, HhNetworm()
url1 = "http://psfw.jd.com/help/front/initArea.do?"
url2 = "http://psfw.jd.com/help/front/initCity.do"
url3 = "http://psfw.jd.com/help/front/initArea.do"
url4 = "http://psfw.jd.com/help/front/initFouth.do"
try:
js1 = hhnetworm.getRes(url1, method='p', result='j')
for aa in js1['result']['resultList']:
province, province_id = aa['name'], str(aa['id'])
js2 = hhnetworm.getRes(url2,
method='p',
data={'provinceId': province_id},
result='j')
for bb in js2['result']['resultList']:
city, city_id = bb['name'], str(bb['id'])
js3 = hhnetworm.getRes(url3,
method='p',
result='j',
data={
'provinceId': province_id,
'cityId': city_id
})
for cc in js3['result']['resultList']:
district, district_id = cc['name'], str(cc['id'])
js4 = hhnetworm.getRes(url4,
method='p',
result='j',
data={
'provinceId': province_id,
'cityId': city_id,
'areaId': district_id
})
if js4['result']['hasNext']:
for dd in js4['result']['resultList']:
dic = {
'province': province,
'city': city,
'district': district,
'area': dd['name']
}
rt_arr.append(dic)
print(dic)
else:
dic = {
'province': province,
'city': city,
'district': district,
'area': ''
}
rt_arr.append(dic)
print(dic)
HhTime.costPrinter(st_time, pjName='京东地址库', dataArr=rt_arr)
finish = True
except:
print("----------Wrong: {}".format('京东地址库'))
traceback.print_exc()
finally:
return rt_arr if finish else []