Question

我正在为此网站http://www.starcitygames.com/catalog/category/Duel%20Decks%20Venser%20vs%20Koth编写一个网络抓取程序，并且在网站的数据表中，有一个卡名具有两种不同的条件/价格/库存的情况，而我同时需要信息，但您会在所附图片中看到，卡名仅在第一行而不是底部。因此，例如，对于以太膜，它将输出卡名称以及所有其他信息，但是在下一行中，我将获得所有其他信息，但卡名称将为Null。有没有办法喜欢在卡名是否为null的情况下设置if语句或其他可以查看的地方，如果这样，则将卡名设置为等于上一个条目。我需要用正确的卡名替换Null字符。

SplashSpider.py

import csv
from scrapy.spiders import Spider
from scrapy_splash import SplashRequest
from ..items import GameItem

# process the csv file so the url + ip address + useragent pairs are the same as defined in the file # returns a list of dictionaries, example:
# [ {'url': 'http://www.starcitygames.com/catalog/category/Rivals%20of%20Ixalan',
#    'ip': 'http://204.152.114.244:8050',
#    'ua': "Mozilla/5.0 (BlackBerry; U; BlackBerry 9320; en-GB) AppleWebKit/534.11"},
#    ...
# ]
def process_csv(csv_file):
    data = []
    reader = csv.reader(csv_file)
    next(reader)
    for fields in reader:
        if fields[0] != "":
            url = fields[0]
        else:
            continue # skip the whole row if the url column is empty
        if fields[1] != "":
            ip = "http://" + fields[1] + ":8050" # adding http and port because this is the needed scheme
        if fields[2] != "":
            useragent = fields[2]
        data.append({"url": url, "ip": ip, "ua": useragent})
    return data


class MySpider(Spider):
    name = 'splash_spider'  # Name of Spider

    # notice that we don't need to define start_urls
    # just make sure to get all the urls you want to scrape inside start_requests function

    # getting all the url + ip address + useragent pairs then request them
    def start_requests(self):

        # get the file path of the csv file that contains the pairs from the settings.py
        with open(self.settings["PROXY_CSV_FILE"], mode="r") as csv_file:
           # requests is a list of dictionaries like this -> {url: str, ua: str, ip: str}
            requests = process_csv(csv_file)

        for req in requests:
            # no need to create custom middlewares
            # just pass useragent using the headers param, and pass proxy using the meta param

            yield SplashRequest(url=req["url"], callback=self.parse, args={"wait": 3},
                    headers={"User-Agent": req["ua"]},
                    splash_url = req["ip"],
                    )
    # Scraping
    def parse(self, response):
        item = GameItem()
        for game in response.css("tr[class^=deckdbbody]"):
            # Card Name
            item["card_name"] = game.css("a.card_popup::text").extract_first()
            item["condition"] = game.css("td[class^=deckdbbody].search_results_7 a::text").get()

            item["stock"] = game.css("td[class^=deckdbbody].search_results_8::text").extract_first()
            item["price"] = game.css("td[class^=deckdbbody].search_results_9::text").extract_first()

            yield item

样本输出

{"card_name": "\nAether Membrane", "Condition": "NM/M", "stock": "93", "Price": "$0.59"},
{"card_name": null, "Condition": "PL", "stock": "59", "Price": "$0.49"},
{"card_name": "\nAngelic Shield", "Condition": "NM/M", "stock": "35", "Price": "$0.25"},
{"card_name": "\nAnger", "Condition": "NM/M", "stock": "9", "Price": "$1.49"},
{"card_name": null, "Condition": "PL", "stock": "49", "Price": "$1.19"},
{"card_name": "\nArmillary Sphere", "Condition": "NM/M", "stock": "87", "Price": "$0.25"},
{"card_name": "\nAugury Owl", "Condition": "NM/M", "stock": "Out of Stock", "Price": "$0.29"},

Answer 1

就像评论所说的那样，可以解决问题：

 for game in response.css("tr[class^=deckdbbody]"):
            saved_name  = game.css("a.card_popup::text").extract_first() or saved_name
            item["card_name"] = saved_name.strip()

            if item["card_name"] != None:
                saved_name = item["card_name"].strip()
            else:
                item["card_name"] = saved_name

            item["Condition"] = game.css("td[class^=deckdbbody].search_results_7 a::text").get()
            item["stock"] = game.css("td[class^=deckdbbody].search_results_8::text").extract_first()
            item["Price"] = game.css("td[class^=deckdbbody].search_results_9::text").extract_first()

            yield item

抓取网站时获取空输出

1 个答案: