def sixlucky_parse_list_file(main_cat, sub_cat, list_file, db_name = 'test.db'):
printf("\n==> Start to parse list file: %s ...", list_file)
global commodity_index
if list_file != '':
f = open( list_file , 'r' )
html_text = f.read()
f.close()
if len(html_text) <= 0:
return
ret = {}
ret = sixlucky_parse_pages.parse_list_page(html_text, True, ret)
list_dump = {'list_file' : list_file}
list_dump['commodities'] = []
for commodity_url in ret['link']:
try:
printf('commodity_index: %d', commodity_index)
m = {'main_cat' : main_cat, 'sub_cat' : sub_cat}
m = sixlucky_dump_and_parse_commodity(commodity_url, main_cat, sub_cat, commodity_index, m)
list_dump['commodities'].append(m)
commodity_index += 1
#if i >= 3:
# break # dump leading 3 only because we're still debugging
except Exception, e:
printf("Parse commodity fails ...")
traceback.print_exc()
finally:
def sixlucky_dump_sub_category(url, main_cat, sub_cat):
printf("\n==> Start to parse category url: %s, main_cat: %s, sub_cat: %s ...", url, main_cat, sub_cat)
global sixlucky_working_directory
i = 0
# Category with Referer
#url = 'http://iqc.com.tw/List/2/'
# Return here for debugging
#return
printf("List is %d", str.find(url, "List"))
sixlucky_working_directory = url[str.find(url, "List"):]
html_text = sixlucky_dump_list_page(url, main_cat = main_cat, sub_cat = sub_cat, index = i)
# Parse html page
if len(html_text) <= 0:
print("Can not get list page html_text, len = 0")
return
ret = sixlucky_parse_pages.parse_list_page(html_text, True, ret={})
print("ret['total_product_counts'] = %d", ret['total_product_counts'])
# Calculate pages in this category
page_count = 0
if ret['total_product_counts'] > 0:
page_count = ret['total_product_counts']/18 + 1
if page_count > 10:
page_count = 10
# Fetch page from 2 ~ end
for i in range(1, page_count):
time.sleep(random.random()*10)
url = "http://www.6lucky.com.tw/showroom/" + ret["list_link"][i]
html_text = sixlucky_dump_list_page(url, main_cat = main_cat, sub_cat = sub_cat, index = i)