爬蟲抓取BOSS公司名稱

抓取公司名稱

import requests
import chardet
import lxml
import lxml.etree
import re
import time

headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36",
    "cookie": "lastCity=101010100; _uab_collina=156869286291557668962527; __c=1569067353; __g=-; __l=l=%2Fwww.zhipin.com%2F&r=https%3A%2F%2Fwww.baidu.com%2Flink%3Furl%3DqJ-Tr2KoH8BeyIviFSSBz9uO0qL79FbOYmo3ae9MBwRxEqIW5Kr7eP0z6AYhC2-u%26wd%3D%26eqid%3Dfe8294f4002c5c78000000045d861155&friend_source=0&friend_source=0; __a=2885020.1568692863.1568692863.1569067353.50.2.46.50; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1568692863,1569067353,1569069941,1569069971; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1569069971; __zp_stoken__=c871hXl98mLotgIH1hyR4Kl1g7052ZLS0x%2BtOVl%2FGWCroyHsvr0ZvRNkXzV0hbDrSTxhu4U3uofg5i5FSkOSdFeoYQ%3D%3D",
    "sec-fetch-mode": "same-origin"
}
for it in range(10):
    it = it + 1
    url = "https://www.zhipin.com/gongsi/?page=" + str(it) + "&ka=page-" + str(it)
    # print(url)
    time.sleep(1)
    pagetxt = requests.get(url, headers=headers).content
    # print(pagetxt)
    myxml = lxml.etree.HTML(pagetxt)  # 編碼
    mytable = myxml.xpath("//*[@class=\"conpany-text\"]/h4/text()")
    print(mytable)