标签：文字 request str string col tostring win64 win art
import requests
from lxml import etree
import time
headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36‘,
‘Cookie‘: ‘gr_user_id = c6f58a39 - ea25 - 4f58 - b448 - 545070192c4e;59a81cc7d8c04307ba183d331c373ef6_gr_session_id = e8e4b66f - 440a - 4ae7 - a76a - fe2dd2b34a26;59a81cc7d8c04307ba183d331c373ef6_gr_last_sent_sid_with_cs1 = e8e4b66f - 440a - 4ae7 - a76a - fe2dd2b34a26;59a81cc7d8c04307ba183d331c373ef6_gr_last_sent_cs1 = N % 2FA;59a81cc7d8c04307ba183d331c373ef6_gr_session_id_e8e4b66f - 440a - 4ae7 - a76a - fe2dd2b34a26 = true;grwng_uid = 9ec14ad9 - 5ac0 - 4bb1 - 81c1 - bc60d2685710;abtest_ABTest4SearchDate = b;xzuuid = 79426b52;_uab_collina = 154660443606130958890473;TY_SESSION_ID = 907f32df - c060 - 49ca - b945 - 98215cc03475;rule_math = pvzq3r06hi‘}
def get_name(url):
res = requests.get(url,headers = headers)
html = etree.HTML(res.text)
result = etree.tostring(html)
infos = html.xpath(‘//*[@class="article block untagged mb15 typs_hot"]‘)
try:
for info in infos:
name = info.xpath(‘div[1]/a[2]/h2/text()‘)
if len(name) != 0:
print(name[0])
except Exception as e:
print(e)
if __name__ == ‘__main__‘:
urls = [‘https://www.qiushibaike.com/text/page/{}/‘.format(number) for number in range(1, 14)]
for url in urls:
get_name(url)
print("------------------这是一页的分割线----------------------------")
time.sleep(1)``
获取糗事百科网“文字”栏目所有的用户ID。重点关注xpath语法；
html.xpath(‘//*[@class="article block untagged mb15 typs_hot"]‘)获取所有段子DIV。返回一个对象存储在列表中。
name = info.xpath(‘div[1]/a[2]/h2/text()‘) 再从每一个对象中获取ID。标签：文字 request str string col tostring win64 win art
原文地址：http://blog.51cto.com/12884584/2352025
