cwx/ComicScrapy
1
0 Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
cwx committed 2023-08-06 20:58:47 +08:00
1 parent ae3826b671
commit a3b50fb923
2 files changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

Comics/settings.py
+1 -1
View File
@@ -14,7 +14,7 @@ BOT_NAME = 'Comics'
SPIDER_MODULES = ['Comics.spiders'] SPIDER_MODULES = ['Comics.spiders']
NEWSPIDER_MODULE = 'Comics.spiders' NEWSPIDER_MODULE = 'Comics.spiders'
BASE_OUTPUT = "/home/cwx/Dev/Comics" BASE_OUTPUT = "/mnt/Comics"
OUTPUT_DIR = os.path.join(BASE_OUTPUT, "output") OUTPUT_DIR = os.path.join(BASE_OUTPUT, "output")
# Crawl responsibly by identifying yourself (and your website) on the user-agent # Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'Comics (+http://www.yourdomain.com)' #USER_AGENT = 'Comics (+http://www.yourdomain.com)'
Comics/spiders/rm_comic.py
+1 -1
View File
@@ -7,7 +7,7 @@ from Comics.settings import PROJECT_KEY
class RmComicSpider(scrapy.Spider): class RmComicSpider(scrapy.Spider):
name = 'rm_comic' name = 'rm_comic'
allowed_domains = ['rouman5.com'] allowed_domains = ['roum1.xyz']
main_url = 'https://'+allowed_domains[0] main_url = 'https://'+allowed_domains[0]
start_urls = main_url+'/books' start_urls = main_url+'/books'