网络上搜索,只得到一些直接用最终url爬取360个人图书馆的知识。下面代码是以输入关键字以及指定起始页码而采集到最终文档的url列表,返回结果为列表URL,主页中有相关的视频,下面是代码(个人比较中意头条文章中插入代码的功能),复制代码到python相关ide中后,每行代码间会出现空白行,大家要注意了:
以下内容纯属只为交流,请勿用于商业用途,如若产生诉讼与纠纷请自行承担。
# coding = gbk
import hashlib
import time
import requests
from lxml import etree
from multiprocessing.dummy import Pool as pl
import pythoncom
# 获取360个人文库内容
class lib360Person():
"""
加密字符串样式:'360docend=10sort=3start=1word=javascript'
"""
def __init__(self,params):
self.headers = {
"Referer": "http://www.360doc.com/search.html",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36",
}
self.keyword = params["keyword"] # 关键字
self.start = params["start"] # 开始页
self.end = params["end"] # 结束页
self.thread = params["thread"] # 线程数
self.url_lists = []
self.lastUrl_lists = [] # 存放最终的页面url
def run(self):
# 获取每页列表的url
self.getUrl()
# 获取每个列表中的详细url,一起放入lastUrl_lists中并返回
pool = pl(self.thread)
pool.map(self.parseUrl, self.url_lists)
pool.close()
pool.join()
pythoncom.CoUninitialize()
return self.lastUrl_lists
def parseUrl(self,url):
res = requests.get(url, headers=self.headers)
html = etree.HTML(res.text)
url_lists = html.xpath("//span[@class='wzbtlista font14']/a/@href")
self.lastUrl_lists.extend(url_lists)
# 获取编码后的url地址
def getUrl(self):
for i in range(self.start,self.end+1):
signStr = "360docend={}sort=3start={}word={}".format(i*10,(i-1)*10+1,self.keyword)
timeValue = int(time.time() * 1000)
self.url_lists.append("http://www.360doc.com/search/searchArt.ashx?word={}&sort=3&start={}&end={}&sign={}&_={}".format(self.keyword,(i-1)*10+1,i*10,self.md5Code(signStr),timeValue))
# 获取MD5编码后的内容
def md5Code(self,str):
hs = hashlib.md5()
hs.update(str.encode("utf8"))
return hs.hexdigest()
if __name__ == '__main__':
params = {
"keyword":"javascript", # 搜索的关键字
"start":5, # 开始页码
"end":10, # 结束页码
"thread":1, # 线程数
}
a = lib360Person(params) # 实例化
url_lists = a.run() # 运行实例a的run方法
print(len(url_lists))