爬取XMOL上的文献

爬取X-MOL，代码如下
name和password是你自己的账号密码，希望大佬指正

```python
import requests
from bs4 import BeautifulSoup
import json
from urllib.parse import urlencode
from selenium import webdriver
import time
#导入动作练 
from selenium.webdriver import ActionChains
import time



def se_login():
	
	options = webdriver.FirefoxOptions()
	#设置无头化过程
	options.add_argument("--headless")
	options.add_argument("--disable-gpu")

	options.binary_location =  "D://火狐浏览器//firefox.exe"
	browser = webdriver.Firefox(executable_path = 'E://Python37//geckodriver.exe', options = options)
	#time.sleep(3)
	browser.get('https://www.x-mol.com/login')
	username = browser.find_element_by_id('username')
	username.send_keys('name')
	password = browser.find_element_by_id('password')
	password.send_keys('password')

	btn = browser.find_element_by_xpath('/html/body/div[2]/div[2]/div/div/div[2]/div[3]/form/div[4]/div/input')
	btn.click()
	global cookie
	cookie = browser.get_cookies()
	#jsoncookies = json.dumps(cookie)#将cokie转化为字符串才可以保存为text文本中
	#with open('C:\\Users\\YJS\\Desktop\\123.txt', 'w') as f:
	#	f.write(jsoncookies)
	#print(type(cookie),'\n',cookie)
	global cookiestr
	list1  = []
	for item in cookie:	
		list1.append(item['name'] + '=' + item['value'] + ';')
	#print(list1)
	cookiestr = ''.join(list1)
	#print(cookiestr)

	browser.quit()
	
	




#模拟登陆不成功，我直接在网页上获取内容

base_url = "https://www.x-mol.com/paper/search/q?"
def get_text(search, pageindex):
	data = {'option':search, 'pageIndex':pageindex}
	headers = {
	'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0',
	'Referer':'https://www.x-mol.com/',
	'Host':'www.x-mol.com',
	'Cookie':cookiestr
	}
	url = base_url + urlencode(data)
	try:
		r = requests.get(url, headers = headers)
		if r.status_code == 200:
			print('\n','要检索的网址为：', r.url)
			time.sleep(2)
			print(r.status_code)
			return r.text
	except Exception as e:
		print(str(e))	


def ana_page(html):
	soup = BeautifulSoup(html,'lxml')
	items = soup.find_all(name = 'div',attrs = {'class':'magazine-senior-search-results-list-right'})
	for item in items:
		#print(item)
		title = item.find(name = 'div', attrs = {'class':'it-bold space-bottom-m10'}).text.strip()#.string只能回去一个tag节点的文本值，节点多了就不知道是哪一个节点了，就会返回None
		periodical = item.find(name = "em", attrs = {'class':'it-blue'}).text
		#print(periodical)
		global IF
		IF = item.find(name = 'span', attrs = {'style':'color: #FF7010;'}).text
		author = item.find_all(name = 'div', attrs = {'class':'div-text-line-one it-new-gary'})[1].text.strip()
		#print(author)
		#all = item.find(name = 'div', attrs = {'class':'div-text-line-one it-new-gary'}).text
		all = item.find(name = 'span', attrs = {'style':'color: #FF7010;'}).next_sibling.string
		
		(date,DOI) = all.split(',')
		DOI = DOI.split(':')
		date = date.split(':')[1].strip()

		
		yield {
		'title':title,
		'date':date,
		'periodical':periodical,
		'IF':IF,
		'DOI':DOI[1].strip(),
		'author':author
		}







def main():
	if judge == "y":
		for pageindex in range(1,int(Range) + 1):
			html = get_text(search, pageindex)
			generator = ana_page(html)
			for g in generator:
				if float(g['IF']) >= 10.0:
					print(g)


	else:
		for pageindex in range(1,int(Range) + 1):
			html = get_text(search, pageindex)
			generator = ana_page(html)
			for g in generator:
				print(g)




#if get_text()

se_login()

while True:
	search = input('请输入要搜索的内容：')
	Range = input('请输入检索页面数量:')
	judge = input('是否只输出IF>= 10的文献：')
	main()