35 lines
1,010 B
Python
35 lines
1,010 B
Python
|
import scrapy
|
||
|
|
import sys
|
||
|
|
import requests
|
||
|
|
import io
|
||
|
|
|
||
|
|
sys.path.append("../../convert/31-2")
|
||
|
|
from db import *
|
||
|
|
|
||
|
|
db.bind(provider="sqlite", filename="../../clean/31-2/data.sqlite3")
|
||
|
|
db.generate_mapping()
|
||
|
|
|
||
|
|
|
||
|
|
class OutfitSpider(scrapy.Spider):
|
||
|
|
name = "outfits"
|
||
|
|
start_urls = [
|
||
|
|
"https://deadcells.fandom.com/wiki/Outfits",
|
||
|
|
]
|
||
|
|
|
||
|
|
def parse(self, response):
|
||
|
|
for quote in response.css(".wikitable tbody tr"):
|
||
|
|
name_en = quote.css("td:nth-child(2) > span:last-child::text").get()
|
||
|
|
if not name_en:
|
||
|
|
print(name_en)
|
||
|
|
continue
|
||
|
|
preview = quote.css(
|
||
|
|
"td:nth-child(6) > span:last-child a::attr('href')"
|
||
|
|
).get()
|
||
|
|
try:
|
||
|
|
r = requests.get(preview)
|
||
|
|
with db_session:
|
||
|
|
w = Outfit.select(name_en=name_en).first()
|
||
|
|
w.preview = io.BytesIO(r.content).getbuffer().tobytes()
|
||
|
|
except:
|
||
|
|
print("Preview not available.")
|