def _get_byb_merchant(self, html_code=None):
if html_code is None:
return '', ''
parser = GoodsParser(html_code)
sname = parser._get_seller_name()
seller_id = parser._get_seller_id()
print('_get_byb_merchant.sname', sname)
print('_get_byb_merchant.seller_id', seller_id)
if not sname:
seller_id = ''
return sname, seller_id
def make_url(asin, cid=0, url_type='goods', urltitle='', sessionId=''):
url_tuple = tuple()
if url_type == 'goods':
url, referer = GoodsParser.make_goods_url(asin,
urltitle=urltitle,
sessionId=sessionId)
url_tuple = (url, referer)
if url_type == 'reviews':
url = ReviewsParser.make_reviews_url(asin, urltitle=urltitle)
url_tuple = (url, )
if url_type == 'tosell':
url = TosellParser.make_tosell_url(asin)
url_tuple = (url, )
if url_type == 'keyword':
url = GoodsParser.make_search_url(asin, cid)
url_tuple = (url, )
return url_tuple
def get_brand_from_parser(asin):
# 根据asin获取url
url, refer = BaseCrawler.make_url(asin)
# 调用下载器方法获取页面数据
html_code = get_data_from_requests(url)
# 调用商品解析的方法获取页面的品牌信息
print(222)
brand = GoodsParser(html_code)._get_brand()
return brand
def parser(self,
html,
html_type='',
asin='',
ip='',
url='',
ua='',
info_log=None,
debug_log=None,
monitor_type=0,
cookie=None,
tosellSum=None,
goods_html_code=None):
'''只写了商品、评论、跟卖, 评论的html要求是一个html_list其余模块根据需要覆写此方法'''
result = ()
is_error = False
if html_type == 'goods':
try:
goods_datas, bsr_data = GoodsParser().parser_goods(
html,
asin,
monitor_type,
ip=ip,
ua=ua,
debug_log=debug_log,
download_url=url,
cookies=cookie)
result = (goods_datas, bsr_data)
except Exception as e:
is_error = True
self.debug_log.error('[%s] goods parser解析 [%s] 时 [%s]' %
(ip, url, e))
if html_type == 'reviews':
try:
reviews_datas = ReviewsParser().reviews_parser(
html, asin, ip=ip, download_url=url)
result = (reviews_datas, )
except Exception as e:
is_error = True
self.debug_log.error('[%s] reviews parser解析 [%s] 时 [%s]' %
(ip, url, e))
if html_type == 'tosell':
try:
tosell_info = TosellParser().tosell_parser(
html,
asin,
tosellSum,
ip=ip,
download_url=url,
goods_html_code=goods_html_code)
result = (tosell_info, )
except Exception as e:
is_error = True
self.debug_log.error('[%s] tosell parser解析 [%s] 时 [%s]' %
(ip, url, e))
return result, is_error
def get_brand_from_parser(asin, debug_log):
# 根据asin获取url
urls = BaseCrawler.make_url(asin)
url = urls[0]
refer = urls[1]
# 获取ua
ua = UaPond.get_new_ua()
cookies = ''
ip = ''
ipQ = ''
# 调用下载器方法获取页面数据
html_data, cookie, is_error = get_html_useRequest(url,
ua,
ip,
cookies,
debug_log,
refer,
ipQ,
url_type='goods',
asin=asin)
# 调用商品解析的方法获取页面的品牌信息
brand = GoodsParser(html_data)._get_brand()
return brand
def get_to_sell_price(html_code=None):
return GoodsParser(html_code)._to_price(html_code)
def get_to_sell_sum(html_code=None):
return GoodsParser(html_code)._to_sell(html_code)
from Crawler.goodsParser import GoodsParser
goods = GoodsParser()
with open('1.html', 'r', encoding='utf8') as f:
html = f.read()
goods.parser_goods(html, 'the_asin', '')
count = goods._get_review_count(html_code=html)
code = goods._get_review_rating(html_code=html)
print(count)
print(code)
def download(self, ip, asin_or_kw, url_dict):
url_type = self.url_type
asin = asin_or_kw
monitor_type = url_dict.get('mtp') or 1
print('url type: ', url_type)
url_md5key = url_dict.get('md5') or ''
if not url_md5key:
url_md5key = self.get_md5_key(asin + url_type)
startTime = return_PST().strftime("%Y-%m-%d %H:%M:%S")
time_now = lambda: time.time()
time1 = time_now()
ua = self.get_ua()
self.debug_log.debug('goods ua: %s' % (ua))
# value_str = ip + ua
# self.debug_log.debug('goods value_str: %s' % (value_str))
# cookMd5key = self.get_md5_key(value_str)
cookMd5key = ''
cookie = self.get_cookie(cookMd5key)
print('\ngoodsCookie: ', cookie)
# url_title = urlQ.get_urlTitle_from_string(asin)
url_title = ''
sessionId = ''
# if cookie:
# sessionId = cookie.get('session-id')
retry = False
old_dnum = url_dict.get('dnum') or 0
if old_dnum > 3:
retry = True
url, referer = GoodsParser.make_goods_url(asin,
urltitle=url_title,
sessionId=sessionId,
retry=retry)
cookies = cookie
print('goods referer: %s' % (referer))
print('[ip %s] 工作中... [%s]' % (ip, url))
if url:
print('goods_url: ', url)
html, cookiesObj, is_error = self.get_html(url,
ua,
ip,
cookies,
referer,
url_type=url_type,
asin=asin)
print('这是HTML')
# with open('data/devtest/6_1.html', 'w', encoding='utf8') as f:
# f.write(html)
durl = url_dict.get('durl') or []
durl.append(url)
url_dict['durl'] = list(set(durl))
url_dict['dnum'] = old_dnum + 1
if is_error:
self.the_url_is_discard(asin, url_dict, url_type, url_md5key)
msgInt = 6
proxyInfo = 'get Html error'
self.record_log(asin, time1, msgInt, url_type, startTime, ip,
proxyInfo)
else:
analyze = self.analyze_html(html,
cookie,
cookiesObj,
ip,
asin_or_kw,
url_dict,
cookMd5key,
time1,
startTime,
html_type=url_type)
if analyze and analyze != 404:
# 获取url_title 并保存
# self.save_url_title(asin, html)
cook = cookie
if not cookie:
cook = cookiesObj
result, is_error = self.parser(html,
html_type=url_type,
asin=asin,
ip=ip,
ua=ua,
debug_log=self.debug_log,
monitor_type=monitor_type,
cookie=cook,
url=url)
if is_error:
self.the_url_is_discard(asin, url_dict, url_type,
url_md5key)
msgInt = 3
proxyInfo = 'get data error'
self.record_log(asin, time1, msgInt, url_type,
startTime, ip, proxyInfo)
else:
if not result:
self.the_url_is_discard(asin, url_dict, url_type,
url_md5key)
msgInt = 2
proxyInfo = 'get data defeated'
self.record_log(asin, time1, msgInt, url_type,
startTime, ip, proxyInfo)
else:
goods_datas = result[0]
if goods_datas:
print('goods_datas:', goods_datas)
qty, qtydt = inv_start(asin, html, cook, ua,
goods_datas[asin])
print('qty, qtydt:', qty, qtydt)
goods_datas[asin]['quantity'] = qty
goods_datas[asin]['qtydt'] = qtydt
print('goods_datas.add(qty, qtydt):',
goods_datas)
bsr_data = result[1]
data_bytes = pickle.dumps(goods_datas)
if bsr_data:
# print('bsr_data1', bsr_data)
bsrData_bytes = pickle.dumps(bsr_data)
# print('bsrData_bytes', bsrData_bytes)
self.dataQ.add_bsrData_to_queue(
bsrData_bytes)
# print('bsr data ok', bsr_data)
# from pprint import pprint
# pprint(goods_datas)
result1 = self.dataQ.add_goods_data_to_queue(
data_bytes)
print(result1)
if not result1:
sys.exit()
# self.dataQ.record_data_ok_times()
# self.dataQ.record_goods_ok_times()
self.save_success_asin_keyword(
asin, url_type=url_type)
msgInt = 1
proxyInfo = 'get data success'
self.record_log(asin, time1, msgInt, url_type,
startTime, ip, proxyInfo)
else:
self.the_url_is_discard(asin, url_dict, url_type,
url_md5key)
time.sleep(1)
else:
print(url_type, '没有url')
self.the_url_is_discard(asin, url_dict, url_type, url_md5key)
time.sleep(1)
def save_url_title(self, asin, html):
urlTitle = GoodsParser.get_urltitle(asin, html)
if urlTitle and len(urlTitle) <= 72:
urlQ.add_urlTitle_to_string(asin, urlTitle)
def make_search_url(self, kw, cid):
search_url = GoodsParser.make_search_url(kw, cid)
return search_url
def is_page_not_found(self, html):
return GoodsParser.is_page_not_found(html)
def is_RobotCheck(self, html):
return GoodsParser.is_RobotCheck(html)
def download(self, asin_or_kw, url_dict):
print(asin_or_kw, url_dict)
url_type = self.url_type
print(url_type)
asin = asin_or_kw
monitor_type = url_dict.get('mtp') or 1
print('url type: ', url_type)
url_md5key = url_dict.get('md5') or ''
if not url_md5key:
url_md5key = self.get_md5_key(asin + url_type)
startTime = return_PST().strftime("%Y-%m-%d %H:%M:%S")
time_now = lambda: time.time()
time1 = time_now()
retry = False
old_dnum = url_dict.get('dnum') or 0
if old_dnum > 3:
retry = True
url, referer = GoodsParser.make_goods_url(asin, retry=retry)
if url:
print('goods_url: ', url)
html, cookiesObj, is_error = self.get_html(url,
referer=referer,
url_type=url_type,
asin=asin)
print('is_error:', is_error)
durl = url_dict.get('durl') or []
durl.append(url)
url_dict['durl'] = list(set(durl))
url_dict['dnum'] = old_dnum + 1
if is_error:
self.the_url_is_discard(asin, url_dict, url_type, url_md5key)
msgInt = 6
proxyInfo = 'get Html error'
self.record_log(asin, time1, msgInt, url_type, startTime,
proxyInfo)
else:
analyze = self.analyze_html(html,
asin_or_kw,
url_dict,
time1,
startTime,
html_type=url_type)
if analyze and analyze != 404:
result, is_error = self.parser(html,
html_type=url_type,
asin=asin,
debug_log=self.debug_log,
monitor_type=monitor_type,
url=url)
if is_error:
self.the_url_is_discard(asin, url_dict, url_type,
url_md5key)
msgInt = 3
proxyInfo = 'get data error'
self.record_log(asin, time1, msgInt, url_type,
startTime, proxyInfo)
else:
if not result:
self.the_url_is_discard(asin, url_dict, url_type,
url_md5key)
msgInt = 2
proxyInfo = 'get data defeated'
self.record_log(asin, time1, msgInt, url_type,
startTime, proxyInfo)
else:
goods_datas = result[0]
if goods_datas:
cookies, headers = cookiesObj
user_anget = headers.get('User-Agent')
print(user_anget)
from pprint import pprint
pprint(cookies)
pprint(goods_datas)
msgInt = 1
proxyInfo = 'get data success'
log_param = (asin, time1, msgInt, url_type,
startTime, proxyInfo)
start(asin=asin,
goods_datas=goods_datas,
user_anget=user_anget,
url_dict=url_dict,
goods_html=html,
cookies=cookies,
log_param=log_param,
crawler_obj=self)
else:
self.the_url_is_discard(asin, url_dict, url_type,
url_md5key)
time.sleep(1)
else:
print(url_type, '没有url')
self.the_url_is_discard(asin, url_dict, url_type, url_md5key)
time.sleep(1)
