def iqc_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 iqc_working_directory
# Category with Referer
#url = 'http://iqc.com.tw/List/2/'
#referer = 'http://iqc.com.tw/List/1/'
#referer = 'http://iqc.com.tw/List/0/1/61'
# Return here for debugging
#return
printf("List is %d", str.find(url, "List"))
iqc_working_directory = url[str.find(url, "List"):]
html_text = iqc_dump_list_page(url)
# Parse html page
if len(html_text) > 0:
ret = iqc_parse_pages.parse_list_page(html_text, True)
# Calculate pages in this category
page_count = 0
if ret['total_product_counts'] > 0:
page_count = ret['total_product_counts']/24 + 1
# Fetch page from 2 ~ end
for i in range(1, page_count):
referer = url
url = 'http://iqc.com.tw/List/' + str(i) + '/'
html_text = iqc_dump_list_page(url)
def sixlucky_parse_list_dir(main_cat, sub_cat, list_dir):
printf("\n=> Start to parse list pages in current directory: %s ...", list_dir)
global sixlucky_working_directory
global commodity_index
sixlucky_working_directory = list_dir
commodity_index = 0
all_files = []
db_name = os.path.join(list_dir, "products.db")
printf("db_name = %s" % db_name)
root = ''
if os.path.exists(db_name):
printf("db exists: %s , skip it", db_name)
return
for root, dirs, files in os.walk(list_dir):
printf("root is %s, dirs is %s, files is %s", root, str(dirs), str(files))
if list_dir == root:
all_files = files
break
for f in all_files:
printf("parsing file: %s ...", f)
try:
if f.startswith("list_"):
sixlucky_parse_list_file(main_cat, sub_cat, os.path.join(root, f), db_name)
pass
except Exception, e:
traceback.print_exc()
def iqc_parse_commodity(barcode, ret = {}):
printf("\n===> Start to dump barcode %s ...", barcode)
# http://iqc.com.tw/Commodities/Detail/176725
url = 'http://iqc.com.tw/Commodities/Detail/' + barcode
target_file = iqc_url_to_local_file(url)
html_text = jagabee_pycurl.pycurl_wrapper_fetch(url, target_file)
if len(html_text) > 0:
iqc_parse_pages.parse_commodities_page(html_text, ret)
# http://iqc.com.tw/Commodity/Detail/176725
url = 'http://iqc.com.tw/Commodity/Detail/' + barcode
target_file = iqc_url_to_local_file(url)
html_text = jagabee_pycurl.pycurl_wrapper_fetch(url, target_file)
if len(html_text) > 0:
iqc_parse_pages.parse_commodity_page(html_text, ret)
return ret
def sixlucky_dump_list_page(url, main_cat = "main_cat", sub_cat = "sub_cat", index = 0):
printf("sixlucky_dump_list_page: url = %s, main_cat = %s, sub_cat = %s " , url, main_cat, sub_cat)
target_file = sixlucky_url_to_local_file(url, main_cat = main_cat, sub_cat = sub_cat, page_type = "list", index = index)
printf('dump %s to target_file: %s ', url, target_file)
# Fetch html page
html_text = jagabee_pycurl.pycurl_wrapper_fetch(url, target_file)
return html_text
def iqc_dump_list_page(url, referer = ''):
printf("iqc_dump_list_page: url = %s " ,url)
target_file = iqc_url_to_local_file(url)
printf('dump %s to target_file: %s , referer: %s', url, target_file, referer)
# Fetch html page
html_text = jagabee_pycurl.pycurl_wrapper_fetch(url, target_file, referer)
return html_text
def sixlucky_dump_and_parse_commodity(url, main_cat = "main_cat", sub_cat = "sub_cat", index = -1, ret = {}):
target_file = sixlucky_url_to_local_file(url, main_cat, sub_cat, "commodity", index)
printf("\n===> Start to dump commodity page url: %s to target_file: %s ...", url, target_file)
html_text = jagabee_pycurl.pycurl_wrapper_fetch(url, target_file)
if len(html_text) > 0:
sixlucky_parse_pages.parse_commodity_page(html_text, ret)
return ret
def sixlucky_url_to_local_file(url, main_cat = "main_cat", sub_cat = "sub_cat", page_type = None, index = -1):
global sixlucky_working_directory
sixlucky_working_directory = sixlucky_get_directory(main_cat, sub_cat)
try:
os.makedirs(sixlucky_working_directory)
except Exception, e:
if e.errno != errno.EEXIST:
printf('sixlucky_url_to_local_file mkdir exception: !!')
traceback.print_exc()
def iqc_dump_main_category(main_cat_dict):
try:
main_cat = main_cat_dict['main_cat']
sub_cats = main_cat_dict['sub_cats']
for sub_cat_dict in sub_cats:
url = 'http://iqc.com.tw/' + sub_cat_dict['url']
sub_cat = sub_cat_dict['sub_cat']
iqc_dump_sub_category(url, main_cat, sub_cat)
except Exception, e:
printf('iqc_dump_main_category exception: !!')
traceback.print_exc()
def sixlucky_dump_main_category(main_cat_dict):
try:
main_cat = main_cat_dict['main_cat']
sub_cats = main_cat_dict['sub_cats']
for sub_cat_dict in sub_cats:
url = sub_cat_dict['url']
sub_cat = sub_cat_dict['sub_cat']
sixlucky_dump_sub_category(url, main_cat, sub_cat)
time.sleep(10)
except Exception, e:
printf('sixlucky_dump_main_category exception: !!')
traceback.print_exc()
def print_usage(cmd):
usage = '''
-m, --parse-main-category=N
Parse main category (index = N)
-s, --parse-sub-category
Parse sub category
-l, --parse-list-file=FILE
Parse a list file
-d, --parse-list-dir=DIR
Parse list files in a directory
-c, --collect-all-db
Collect all database into one
-h, --help
Print this usage
'''
printf(('\n%s usage: ' + usage), cmd)
return
def print_usage(cmd):
usage = '''
-m, --dump-main-category=N
Dump list html pages from sub categories from a main category (index = N)
-s, --dump-sub-category
Dump list html pages from a sub category
-r, dump-commodity-from-sub-category-dirs
Dump commodity pages from sub category dirs
-l, --parse-list-file=FILE
Parse a list file
-d, --parse-list-dir=DIR
Parse list files in a directory
-a, --collect-all-db
Collect all database into one
-h, --help
Print this usage
'''
printf(('\n%s usage: ' + usage), cmd)
return
def iqc_url_to_local_file(url):
global iqc_working_directory
if url[0:7] == 'http://':
# Replace filename
url = url[7:] # Remove 'http://' (7 byes)
elif url[0:8] == 'https://':
url = url[8:]
url = string.replace(url, "//", "/")
target_file = string.replace(url, '/', '_') + '.html'
try:
os.makedirs(iqc_working_directory)
except Exception, e:
if e.errno != errno.EEXIST:
printf('iqc_url_to_local_file mkdir exception: !!')
traceback.print_exc()
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)
def main(argv):
dump_main_category = None
dump_sub_category = None
dump_commodity_from_sub_category_dirs = None
parse_list_file = None
parse_list_dir = None
collect_all_db = None
try:
#printf(" argv=%s", str(argv))
opts, other_args = getopt.getopt(argv[1:],"m:srlda",["dump-main-category=", "dump-sub-category", "dump-commodity-from-sub-category-dirs", "parse-list-file", "parse-list-dir", "collect-all-db"])
except getopt.GetoptError:
printf("getopt.GetoptError: ")
traceback.print_exc()
print_usage(argv[0])
sys.exit(-1)
for opt, arg in opts:
if opt in ("-m", "--dump-main-category"):
dump_main_category = int(arg) # index of main category (int)
elif opt in ("-s", "--dump-sub-category"):
dump_sub_category = True
elif opt in ("-r", "--dump-commodity-from-sub-category-dirs"):
dump_commodity_from_sub_category_dirs = True
elif opt in ("-l", "--parse-list-file"):
parse_list_file = True
elif opt in ("-d", "--parse-list-dir"): # A dir containing whole list pages
parse_list_dir = True
elif opt in ("-a", "--collect-all-db"):
collect_all_db = True
if dump_main_category is None and dump_sub_category is None and dump_commodity_from_sub_category_dirs is None and parse_list_file is None and parse_list_dir is None and collect_all_db is None:
print_usage(argv[0])
sys.exit()
return dump_main_category, dump_sub_category, dump_commodity_from_sub_category_dirs, parse_list_file, parse_list_dir, collect_all_db
def main(argv):
parse_main_category = None
parse_sub_category = None
parse_sub_category_dirs = None
parse_list_file = None
parse_list_dir = None
collect_all_db = None
try:
#printf(" argv=%s", str(argv))
opts, other_args = getopt.getopt(argv[1:],"m:srf:d:c",["parse-main-category=", "parse-sub-category", "parse-sub-category-dirs", "parse-list-file=", "parse-list-dir=", "collect-all-db"])
except getopt.GetoptError:
printf("getopt.GetoptError: ")
traceback.print_exc()
print_usage(argv[0])
sys.exit(-1)
for opt, arg in opts:
if opt in ("-m", "--parse-main-category"):
parse_main_category = int(arg) # index of main category (int)
elif opt in ("-s", "--parse-sub-category"):
parse_sub_category = True
elif opt in ("-r", "--parse-sub-category-dirs"):
parse_sub_category_dirs = True
elif opt in ("-f", "--parse-list-file"):
parse_list_file = arg # file (string)
elif opt in ("-d", "--parse-list-dir"):
parse_list_dir = arg # dir (string)
elif opt in ("-c", "--collect-all-db"):
collect_all_db = True
if parse_main_category is None and parse_sub_category is None and parse_sub_category_dirs is None and parse_list_file is None and parse_list_dir is None and collect_all_db is None:
print_usage(argv[0])
sys.exit()
return parse_main_category, parse_sub_category, parse_sub_category_dirs, parse_list_file, parse_list_dir, collect_all_db
def iqc_parse_list_file(main_cat, sub_cat, list_file, db_name = 'test.db'):
printf("\n==> Start to parse list file: %s ...", list_file)
if list_file != '':
f = open( list_file , 'r' )
html_text = f.read()
f.close()
if len(html_text) <= 0:
return
ret = {}
ret = iqc_parse_pages.parse_list_page(html_text, False, ret)
i = 0
list_dump = {'list_file' : list_file}
list_dump['commodities'] = []
list_dump_file = list_file + '.dict' # Dump to a dictionary
for c in ret['link']:
# /Commodities/Detail/171342
# printf('c=%s, type=%s, rindex of "/" is %d', str(c), str(type(c)), string.rindex(c, '/'))
try:
barcode = c[string.rindex(c, '/')+1:]
printf('barcode: %s', barcode)
if (barcode is not None) and (barcode != ''):
commodity = {'barcode' : barcode, 'main_cat' : main_cat, 'sub_cat' : sub_cat}
commodity = iqc_parse_commodity(barcode, commodity)
list_dump['commodities'].append(commodity)
i += 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:
sixlucky_dump_sub_category(url, main_cat, sub_cat)
pass
if dump_commodity_from_sub_category_dirs is not None:
# Define Sub Category Entry
if True: # debug first main category
m = sixlucky_categories.all_categories[10]
main_cat = m['main_cat']
for s in m['sub_cats']:
sub_cat = s['sub_cat']
sub_cat_dir = sixlucky_get_directory(main_cat, sub_cat)
printf ("dump_commodity_from_sub_category_dirs, main_cat = %s, sub_cat = %s, dir = %s", main_cat, sub_cat, sub_cat_dir)
sixlucky_parse_list_dir(main_cat, sub_cat, sub_cat_dir)
else:
for m in sixlucky_categories.all_categories:
main_cat = m['main_cat']
printf ("parse main catetories ... %s", main_cat)
for s in m['sub_cats']:
sub_cat = s['sub_cat']
sub_cat_dir = sixlucky_get_directory(main_cat, sub_cat)
printf ("dump_commodity_from_sub_category_dirs, main_cat = %s, sub_cat = %s, dir = %s", main_cat, sub_cat, sub_cat_dir)
sixlucky_parse_list_dir(main_cat, sub_cat, sub_cat_dir)
