ptt_gossiping

ptt_gossiping

# ptt extraction
import requests
from bs4 import BeautifulSoup
rs = requests.session()
payload = {
'from':'/bbs/Gossiping/index.html',
'yes':'yes'
}
res1 = rs.post("https://www.ptt.cc/ask/over18", data=payload, verify=False)
for i in range(7649, 7600, -1):
    res = rs.get("https://www.ptt.cc/bbs/Gossiping/index%d.html"%i, verify=False)
    soup = BeautifulSoup(res.text)
    tr = soup.select(".r-ent")
    for rec in  tr:
       # print rec.select('.title')[0].text.encode('utf-8').strip()
        if "江" in rec.select('.title')[0].text.encode('utf-8').strip():
            print  rec.select('.title')[0].text.strip()