2020-11-23

2020-11-23  本文已影响0人  Rain师兄

import requests

from lxml import etree

url = 'https://www.guazi.com/hengyang/buy/'

headers = {

'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36',

'cookie':'uuid=fe72b945-5ed5-433e-8a18-23ce0b28f289; clueSourceCode=%2A%2300; ganji_uuid=7966218787922810973167; sessionid=83d28f6d-4b95-4ca7-9e52-a4474ed1ce86; lg=1; cainfo=%7B%22ca_a%22%3A%22-%22%2C%22ca_b%22%3A%22-%22%2C%22ca_s%22%3A%22seo_google%22%2C%22ca_n%22%3A%22default%22%2C%22ca_medium%22%3A%22-%22%2C%22ca_term%22%3A%22-%22%2C%22ca_content%22%3A%22-%22%2C%22ca_campaign%22%3A%22-%22%2C%22ca_kw%22%3A%22-%22%2C%22ca_i%22%3A%22-%22%2C%22scode%22%3A%22-%22%2C%22keyword%22%3A%22-%22%2C%22ca_keywordid%22%3A%22-%22%2C%22display_finance_flag%22%3A%22-%22%2C%22platform%22%3A%221%22%2C%22version%22%3A1%2C%22client_ab%22%3A%22-%22%2C%22guid%22%3A%22fe72b945-5ed5-433e-8a18-23ce0b28f289%22%2C%22ca_city%22%3A%22hengyang%22%2C%22sessionid%22%3A%2283d28f6d-4b95-4ca7-9e52-a4474ed1ce86%22%7D; close_finance_popup=2020-11-23; guazitrackersessioncadata=%7B%22ca_kw%22%3A%22-%22%7D; Hm_lvt_bf3ee5b290ce731c7a4ce7a617256354=1606096713,1606105565; _gl_tracker=%7B%22ca_source%22%3A%22-%22%2C%22ca_name%22%3A%22-%22%2C%22ca_kw%22%3A%22-%22%2C%22ca_id%22%3A%22-%22%2C%22ca_s%22%3A%22self%22%2C%22ca_n%22%3A%22-%22%2C%22ca_i%22%3A%22-%22%2C%22sid%22%3A45317976764%7D; GZ_TOKEN=d7dbWG09RMsVtCS8ShIHxxLvey8aEHZ%2FrvmSYJl5OF%2BPgmp4BUL%2F%2FM0EUSIWLQEcN8SAFj4UqseKGv6rGVlWo0Hai9uuX7wWg%2BAuG4lbNwrS8MBjWQBY5NAyKuobiBXOlJGfjkyVDmmW%2BUxH8w; guaZiUserInfo=5MnskHXiLwWKMXRlmDC%2Bb; userid=750434663; CHDSSO=d7dbWG09RMsVtCS8ShIHxxLvey8aEHZ%2FrvmSYJl5OF%2BPgmp4BUL%2F%2FM0EUSIWLQEcN8SAFj4UqseKGv6rGVlWo0Hai9uuX7wWg%2BAuG4lbNwrS8MBjWQBY5NAyKuobiBXOlJGfjkyVDmmW%2BUxH8w; lng_lat=112.6876_26.88286; gps_type=1; antipas=I6818V2183RF840Gv9TtPTi83; cityDomain=hengyang; user_city_id=207; preTime=%7B%22last%22%3A1606129007%2C%22this%22%3A1606096710%2C%22pre%22%3A1606096710%7D; Hm_lpvt_bf3ee5b290ce731c7a4ce7a617256354=1606129009'

}

def get_detail_urls(url):

    resp = requests.get(url, headers=headers)

    text = resp.content.decode('utf-8')

    pathx = etree.HTML(text)

    fpath = pathx.xpath('//li[@data-scroll-track]/a/@href')

    detail_urls = []

for href in fpath:

piece = 'https://www.guazi.com' + href

        detail_urls.append(piece)

return detail_urls

detail_urls = get_detail_urls(url)

for i in detail_urls:

    resp = requests.get(i,headers=headers)

    xpath = etree.HTML(resp.text)

    r_xpath = xpath.xpath("//h1[@class='titlebox']/text()")

    print(r_xpath[0].strip())

之后可以得到

这里用了cookie,不过cookie隔一段时间会失效,需要重新获取。有些网站不需要headers就能爬取,有些网站不需要cookie就能爬取。
上一篇下一篇

猜你喜欢

热点阅读