python爬取Ajax动态加载网页过程解析

import requests
from lxml import etree
import re
​
url = 'http://www.mca.gov.cn/article/sj/xzqh/2019/'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'}
html = requests.get(url, headers=headers).text
parse_html = etree.HTML(html)
article_list = parse_html.xpath('//a[@class="artitlelist"]')
​
for article in article_list:
  title = article.xpath('./@title')[0]
  # 正则匹配title中包含这个字符串的链接
  if title.endswith('代码'):
    # 获取到第1个就停止即可，第1个永远是最新的链接
    two_link = 'http://www.mca.gov.cn' + article.xpath('./@href')[0]
    print(two_link)
    break

# 爬取二级“假”链接
two_html = requests.get(two_link, headers=headers).text
# 从二级页面的响应中提取真实的链接（此处为JS动态加载跳转的地址）
new_two_link = re.findall(r'window.location.href="(.*?)" rel="external nofollow" rel="external nofollow" ', two_html, re.S)[0]

cursor.execute('select * from version')
result = self.cursor.fetchall()
if result:
  if result[-1][0] == two_link:
    print('已是最新')
  else:
    # 有更新，开始抓取
    # 将链接再重新插入version表记录

import requests
from lxml import etree
import re
import pymysql
class GovementSpider(object):
  def __init__(self):
    self.url = 'http://www.mca.gov.cn/article/sj/xzqh/2019/'
    self.headers = {'User-Agent': 'Mozilla/5.0'}
    # 创建2个对象
    self.db = pymysql.connect('127.0.0.1', 'root', '123456', 'govdb', charset='utf8')
    self.cursor = self.db.cursor()
  # 获取假链接
  def get_false_link(self):
    html = requests.get(url=self.url, headers=self.headers).text
    # 此处隐藏了真实的二级页面的url链接，真实的在假的响应网页中，通过js脚本生成，
    # 假的链接在网页中可以访问，但是爬取到的内容却不是我们想要的
    parse_html = etree.HTML(html)
    a_list = parse_html.xpath('//a[@class="artitlelist"]')
    for a in a_list:
      # get()方法:获取某个属性的值
      title = a.get('title')
      if title.endswith('代码'):
        # 获取到第1个就停止即可，第1个永远是最新的链接
        false_link = 'http://www.mca.gov.cn' + a.get('href')
        print("二级“假”链接的网址为", false_link)
        break
    # 提取真链接
    self.incr_spider(false_link)
  # 增量爬取函数
  def incr_spider(self, false_link):
    self.cursor.execute('select url from version where url=%s', [false_link])
    # fetchall: (('http://xxxx.html',),)
    result = self.cursor.fetchall()

    # not result:代表数据库version表中无数据
    if not result:
      self.get_true_link(false_link)
      # 可选操作: 数据库version表中只保留最新1条数据
      self.cursor.execute("delete from version")

      # 把爬取后的url插入到version表中
      self.cursor.execute('insert into version values(%s)', [false_link])
      self.db.commit()
    else:
      print('数据已是最新,无须爬取')
  # 获取真链接
  def get_true_link(self, false_link):
    # 先获取假链接的响应,然后根据响应获取真链接
    html = requests.get(url=false_link, headers=self.headers).text
    # 从二级页面的响应中提取真实的链接（此处为JS动态加载跳转的地址）
    re_bds = r'window.location.href="(.*?)" rel="external nofollow" rel="external nofollow" '
    pattern = re.compile(re_bds, re.S)
    true_link = pattern.findall(html)[0]

    self.save_data(true_link) # 提取真链接的数据
  # 用xpath直接提取数据
  def save_data(self, true_link):
    html = requests.get(url=true_link, headers=self.headers).text

    # 基准xpath,提取每个信息的节点列表对象
    parse_html = etree.HTML(html)
    tr_list = parse_html.xpath('//tr[@height="19"]')
    for tr in tr_list:
      code = tr.xpath('./td[2]/text()')[0].strip() # 行政区划代码
      name = tr.xpath('./td[3]/text()')[0].strip() # 单位名称
      print(name, code)

  # 主函数
  def main(self):
    self.get_false_link()
if __name__ == '__main__':
  spider = GovementSpider()
  spider.main()

# 查询参数如下：
type: 13 # 电影类型
interval_id: 100:90
action: '[{},{},{}]'
start: 0 # 每次加载电影的起始索引值
limit: 20 # 每次加载的电影数量

import requests
import time
from fake_useragent import UserAgent
class DoubanSpider(object):
  def __init__(self):
    self.base_url = 'https://movie.douban.com/j/chart/top_list?'
    self.i = 0
  def get_html(self, params):
    headers = {'User-Agent': UserAgent().random}
    res = requests.get(url=self.base_url, params=params, headers=headers)
    res.encoding = 'utf-8'
    html = res.json() # 将json格式的字符串转为python数据类型
    self.parse_html(html) # 直接调用解析函数
  def parse_html(self, html):
    # html: [{电影1信息},{电影2信息},{}]
    item = {}
    for one in html:
      item['name'] = one['title'] # 电影名
      item['score'] = one['score'] # 评分
      item['time'] = one['release_date'] # 打印测试
      # 打印显示
      print(item)
      self.i += 1
  # 获取电影总数
  def get_total(self, typ):
    # 异步动态加载的数据 都可以在XHR数据抓包
    url = 'https://movie.douban.com/j/chart/top_list_count?type={}&interval_id=100%3A90'.format(typ)
    ua = UserAgent()
    html = requests.get(url=url, headers={'User-Agent': ua.random}).json()
    total = html['total']

    return total

  def main(self):
    typ = input('请输入电影类型(剧情|喜剧|动作):')
    typ_dict = {'剧情': '11', '喜剧': '24', '动作': '5'}
    typ = typ_dict[typ]
    total = self.get_total(typ) # 获取该类型电影总数量

    for page in range(0, int(total), 20):
      params = {
        'type': typ,
        'interval_id': '100:90',
        'action': '',
        'start': str(page),
        'limit': '20'}
      self.get_html(params)
      time.sleep(1)
    print('爬取的电影的数量:', self.i)
if __name__ == '__main__':
  spider = DoubanSpider()
  spider.main()

ua_list = [
 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0',
 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)',
]

import time
import json
import random
import requests
from useragents import ua_list
class TencentSpider(object):
  def __init__(self):
    self.one_url = 'https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1563912271089&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword=&pageIndex={}&pageSize=10&language=zh-cn&area=cn'
    self.two_url = 'https://careers.tencent.com/tencentcareer/api/post/ByPostId?timestamp=1563912374645&postId={}&language=zh-cn'
    self.f = open('tencent.json', 'a') # 打开文件
    self.item_list = [] # 存放抓取的item字典数据
  # 获取响应内容函数
  def get_page(self, url):
    headers = {'User-Agent': random.choice(ua_list)}
    html = requests.get(url=url, headers=headers).text
    html = json.loads(html) # json格式字符串转为Python数据类型
    return html
  # 主线函数: 获取所有数据
  def parse_page(self, one_url):
    html = self.get_page(one_url)
    item = {}
    for job in html['Data']['Posts']:
      item['name'] = job['RecruitPostName'] # 名称
      post_id = job['PostId'] # postId，拿postid为了拼接二级页面地址
      # 拼接二级地址,获取职责和要求
      two_url = self.two_url.format(post_id)
      item['duty'], item['require'] = self.parse_two_page(two_url)
      print(item)
      self.item_list.append(item) # 添加到大列表中
  # 解析二级页面函数
  def parse_two_page(self, two_url):
    html = self.get_page(two_url)
    duty = html['Data']['Responsibility'] # 工作责任
    duty = duty.replace('\r\n', '').replace('\n', '') # 去掉换行
    require = html['Data']['Requirement'] # 工作要求
    require = require.replace('\r\n', '').replace('\n', '') # 去掉换行
    return duty, require
  # 获取总页数
  def get_numbers(self):
    url = self.one_url.format(1)
    html = self.get_page(url)
    numbers = int(html['Data']['Count']) // 10 + 1 # 每页有10个推荐
    return numbers
  def main(self):
    number = self.get_numbers()
    for page in range(1, 3):
      one_url = self.one_url.format(page)
      self.parse_page(one_url)
    # 保存到本地json文件:json.dump
    json.dump(self.item_list, self.f, ensure_ascii=False)
    self.f.close()
if __name__ == '__main__':
  start = time.time()
  spider = TencentSpider()
  spider.main()
  end = time.time()
  print('执行时间:%.2f' % (end - start))