数据信息采集
我爱扣脚
https://careers.pinduoduo.com/jobs
from DrissionPage import ChromiumPage, ChromiumOptions
def fetch_pinduoduo_jobs( ) :
co = ChromiumOptions( )
path = r'C:\Program Files (x86)\Microsoft\Edge\Application\msedge.exe'
co.set_browser_path( path)
page = ChromiumPage( co)
api_endpoint = '/api/recruit/position/list'
page.listen.start( api_endpoint)
page.get( 'https://careers.pinduoduo.com/jobs#/' )
res = page.listen.wait( )
if res:
print( res._raw_body)
for pagenum in range( 2 , 79 ) :
pagenumstr = f"x://a[text()='{pagenum}']"
next_page_button = page.ele( pagenumstr)
page.listen.start( api_endpoint)
if next_page_button:
next_page_button.click( )
res = page.listen.wait( )
if res:
print( res._raw_body)
page.wait( 5 )
page.close( )
if __name__ == '__main__' :
fetch_pinduoduo_jobs( )