def item_completed(self, results, item, info):
# print(results)
# [(True, {'url': 'https://rpic.douyucdn.cn/acrpic/170827/3034164_v1319.jpg',
# 'checksum': '7383ee5f8dfadebf16a7f123bce4dc45', 'path': 'full/6faebfb1ae66d563476449c69258f2e0aa24000a.jpg'})]
image_path = [x['path'] for ok, x in results if ok]
os.rename(IMAGES_STORE + '/' + image_path[0],
IMAGES_STORE + '/' + item['nickname'] + '.jpg')
if not image_path:
raise scrapy.DropItem('Image Downloaded Failed')
return item
def post_mutasi_form(self, response):
account_id = response.meta["account_id"]
last_day = calendar.monthrange(int(self.year), int(self.month))[1]
today = datetime.date.today()
if today.day < last_day and today.month == int(self.month):
last_day = today.day
from_day = 1
six_month_ago = today - datetime.timedelta(days=6 * 30)
if (today - datetime.timedelta(days=6 * 30)).month == int(self.month):
from_day = today.day
if (
six_month_ago.month < int(self.month)
and int(self.year) > six_month_ago.year
):
raise scrapy.DropItem("only six month query accepted")
data = {
"fromAccountID": account_id,
"fromDay": str(from_day),
"fromMonth": str(self.month),
"fromYear": str(self.year),
"toDay": str(last_day),
"toMonth": str(self.month),
"toYear": str(self.year),
"action": "result",
# 'sortType': 'Date',
# 'orderBy': 'ASC',
# 'searchType': 'R',
}
return scrapy.FormRequest.from_response(
response,
formname="TrxHistoryInqForm",
formdata=data,
callback=self.parse_mutation_page,
# dont_filter=True,
dont_click=True,
meta={"dont_redirect": True},
)
def item_completed(self, results, item, info):
image_paths = [x['path'] for ok, x in results if ok]
if not image_paths:
raise scrapy.DropItem('Image Download Failed')
return item
def item_completed(self, results, item, info):
# 是否下载成功
if not results[0]:
raise scrapy.DropItem('download error')
return item
def item_completed(self, results, item, info):
image_paths = [x['path'] for ok, x in results if ok]
if not image_paths:
raise scrapy.DropItem("Item contains no images")
item['image_paths'] = image_paths
return item