爬虫Task4

模拟登录丁香园，并抓取论坛页面所有的人员基本信息与回复帖子内容

from lxml import etree
from selenium import webdriver
from selenium.common.exceptions import TimeoutException, NoSuchElementException
import requests
import time

browser = webdriver.Chrome()
url = “http://www.dxy.cn/bbs/thread/626626#626626”
browser.get(url)

def login(browser):
try:
browser.find_element_by_xpath(’//[@id=“headerwarp”]/div/div[1]/div/a[1]’).click()
browser.find_element_by_xpath(’/html/body/div[2]/div[2]/div[1]/a[2]’).click()
dxy = browser.find_element_by_name(‘name’)
dxy.clear()
dxy.send_keys(“账号”)
dxy = browser.find_element_by_name(‘password’)
dxy.clear()
dxy.send_keys(“密码”)
browser.find_element_by_xpath(’//[@id=“user”]/div[1]/div[3]/button’).click()
except TimeoutException:
print(“Time out”)

except NoSuchElementException:
print(“No Element”)

def get_information(browser):
print(“登录成功”)
time.sleep(10)
print(“开始获取信息”)
data = requests.get(url).text
s = etree.HTML(data)
for i in range(1, 5):
try:
name = s.xpath(’//[@id=“post_{}”]/table/tbody/tr/td[1]/div[2]/a/text()’.format(i))
info = s.xpath(’//[@id=“post_{}”]/table/tbody/tr/td[2]/div[2]/div[1]/table/tbody/tr/td/text()’.format(i))
info1 = info[0].replace(" “, “”).replace( “\n”, “”)
print(name[0])
print(info1)
except BaseException:
name = s.xpath(’//[@id=“post_{}”]/table/tbody/tr/td[1]/div[2]/a/text()’.format(i))
info = s.xpath(’//[@id=“post_{}”]/table/tbody/tr/td[2]/div[2]/div[2]/table/tbody/tr/td/text()’.format(i))
info1 = info[0].replace(” “, “”).replace(”\n", “”)
print(name[0])
print(info1)
def main():
login(browser)
get_information(browser)
time.sleep(1)

if name == ‘main’:
main()
input("按任意键退出 ")
browser.quit()