Python爬虫JSON及JSONPath运行原理详解

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import urllib2
# json解析库，对应到lxml
import json
# json的解析语法，对应到xpath
import jsonpath
url = "http://www.lagou.com/lbs/getAllCitySearchLabels.json"
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}
request = urllib2.Request(url, headers = headers)
response = urllib2.urlopen(request)
# 取出json文件里的内容，返回的格式是字符串
html = response.read()
# 把json形式的字符串转换成python形式的Unicode字符串
unicodestr = json.loads(html)
# Python形式的列表
city_list = jsonpath.jsonpath(unicodestr, "$..name")
#for item in city_list:
#  print item
# dumps()默认中文为ascii编码格式，ensure_ascii默认为Ture
# 禁用ascii编码格式，返回的Unicode字符串，方便使用
array = json.dumps(city_list, ensure_ascii=False)
#json.dumps(city_list)
#array = json.dumps(city_list)
with open("lagoucity.json", "w") as f:
  f.write(array.encode("utf-8"))

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import urllib2
import json
from lxml import etree
url = "http://www.qiushibaike.com/8hr/page/2/"
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}
request = urllib2.Request(url, headers = headers)
html = urllib2.urlopen(request).read()
# 响应返回的是字符串，解析为HTML DOM模式 text = etree.HTML(html)
text = etree.HTML(html)
# 返回所有段子的结点位置，contains()模糊查询方法，第一个参数是要匹配的标签，第二个参数是标签名部分内容
node_list = text.xpath('//div[contains(@id, "qiushi_tag")]')
items ={}
for node in node_list:
  # xpath返回的列表，这个列表就这一个参数，用索引方式取出来，用户名
  username = node.xpath('./div/a/@title')[0]
  # 取出标签下的内容,段子内容
  content = node.xpath('.//div[@class="content"]/span')[0].text
  # 取出标签里包含的内容，点赞
  zan = node.xpath('.//i')[0].text
  # 评论
  comments = node.xpath('.//i')[1].text
  items = {
    "username" : username,
    "content" : content,
    "zan" : zan,
    "comments" : comments
  }
  with open("qiushi.json", "a") as f:
    f.write(json.dumps(items, ensure_ascii=False).encode("utf-8") + "
")