I am scraping 3 URLs each of which has multiple pages. The first 2 links have 2 pages and the 3rd has 3. Anyways when I scrape them it scrapes page 1 of URL 1 then page 1 of URL 2, instead of page 2 of URL 1. Then it goes back and scrapes page 2 of URL 1 and page 2 of URL 2 and then scrapes all three pages of URL 3 in order. So why is it not scraping them al in order, like page 1,2 of URL 1; page 1,2 of URL 2, and then page 1,2,3 of URL 3. Is there a way to fix it?
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()
saved_name = ""
item["Category"] = response.css("span.titletext::text").extract()
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
next_page = response.xpath('//a[contains(., "- Next>>")]/@href').get()
if next_page is not None:
yield response.follow(next_page, self.parse)
CSV file where URLs are stored
http://www.starcitygames.com/catalog/category/Duel%20Decks%20Venser%20vs%20Koth,204.152.114.229,Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9a1) Gecko/20070308 Minefield/3.0a1
http://www.starcitygames.com/catalog/category/Duel%20Decks%20Zendikar%20vs%20Eldrazi,,
http://www.starcitygames.com/catalog/category/Duels%20of%20the%20Planeswalkers,,
Probably due to the use of concurrence. Try to disable concurrence adding/changing the line below to the settings.py:
CONCURRENT_REQUESTS = 1
EDIT: Oh sorry, let's try another thing. Do you know as the property start_urls works? It is a special property of the Spider class, you can assign a list of URLs to that and it will run each untill the end.
It will work like that:
class MySpyder(Spyder):
name = 'MySpyder'
start_urls = ['url1', 'url2'...]
def parse(self):
[do parse stuff]
you can read your csv and transform it in a list of urls.