mirror of
https://gh.wpcy.net/https://github.com/SoloSynth1/wordpress-scraper.git
synced 2026-04-25 02:35:52 +08:00
19 lines
834 B
Python
19 lines
834 B
Python
from legacy.crawler import crawler
|
|
import os
|
|
|
|
url = "https://blog.malwarebytes.com"
|
|
output_dir = os.path.join('.', 'data', 'blog.malwarebytes.com')
|
|
headers = {
|
|
'Accept':'application/json, text/javascript, */*; q=0.01',
|
|
'Accept-Encoding':'*',
|
|
'Accept-Language':'zh-CN,zh;q=0.8',
|
|
'Cookie': '_ga=GA1.2.1230427134.1541147423; _gid=GA1.2.1527966877.1541383870; _fbp=fb.1.1541468793370.261995265',
|
|
'Connection':'keep-alive',
|
|
'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/70.0.3538.67 Chrome/70.0.3538.67 Safari/537.36',
|
|
'X-Requested-With':'XMLHttpRequest'
|
|
}
|
|
|
|
if __name__ == "__main__":
|
|
from legacy import common_crawl
|
|
wpc = crawler.WordPressCrawler(url, headers, output_dir, crawl_rate=100)
|
|
common_crawl(wpc)
|
