爬虫百度学术

import requests
from bs4 import BeautifulSoup
import re
from lxml import etree
import time
import csv

requests.packages.urllib3.disable_warnings()
#需要生成的cs名字
csv_name = "123.csv"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
}



"""1 第一步"""
# 获取要爬取的分页， 当前第几页，总共要多少条
def get_page_total(p1,total):

    for x in range(p1,total):
        p1=str(x*10)
        url = "https://xueshu.baidu.com/s?wd=journaluri%3A%2820bd239813882ced%29%20applied%20energy&pn="+p1+"&tn=SE_baiduxueshu_c1gjeupa&ie=utf-8&sc_hit=1"
        #print(url)
        print("当前第"+str(x)+"页，共需要"+str(total)+"条")
        get_url(url)
        time.sleep(1)
        #print(x)


"""2 第二步"""
#获取url文章链接地址，-》跳转到详情页
"""
content = ['https://xueshu.baidu.com/usercenter/paper/show?paperid=e04cdee2122f75b0011cc9e7b452d72b&site=xueshu_se',
'https://xueshu.baidu.com/usercenter/paper/show?paperid=9ccc121c6260e006c41c32f04ddf2e85&site=xueshu_se'] ...
"""
def get_url(url):

    r = requests.get(url, headers=headers, verify=False)
    html = r.text
    selector = etree.HTML(html)
    content = selector.xpath('//h3[@class="t c_font"]//a/@href')

    ##获取内容详情,百度文库每页是十条，
    get_page_content(content)


"""3"""
#获取内容详情,百度文库每页是十条，
def get_page_content(detail_url):

    for link in detail_url:
        data = []
        #print(link)
        rr = requests.get(link, headers=headers,verify=False)

        selector = etree.HTML(rr.text)
        #作者
        zuozhe = selector.xpath('//p[@class="author_text"]//span//text()')
        #摘要
        zhaiyao = selector.xpath('//p[@class="abstract"]//text()')

        # print(zuozhe)
        # print(zhaiyao)
        data.append(','.join(zuozhe))
        data.append(','.join(zhaiyao))

        #print(data)
        print("开始写入csv")
        f_csv(data)
        time.sleep(1)

    pass

"""4"""
#写入csv ["111", "222"]

def f_csv(data):

    f = open(csv_name, 'a+', newline='', encoding='utf-8')
    # 2. 基于文件对象构建 csv写入对象
    csv_writer = csv.writer(f)
    #csv_writer.writerow(["作者", '摘要'])
    # 3. 构建列表头
    csv_writer.writerow(data)
    f.close()
    pass


"""run 爬虫"""

#生成csv头部
csv_head = ["作者","摘要"]

#print(csv_head)
f_csv(csv_head)

#获取每篇文章url # 获取要爬取的分页， 当前第几页，总共要多少条

get_page_total(0,1)

#datas = [['M Poeschl', 'S Ward', 'P Owende'],['The energy efficiency of, different, biogas systems'] ]
#
# print(','.join(datas[0]))
# print(','.join(datas[1]))
#f_csv(datas)

标签：get,url,爬虫,print,import,csv,data,百度,学术
来源： https://www.cnblogs.com/wtcl/p/15831406.html