lxml cssselect怎么用
发布网友
发布时间：2022-04-10 15:38
我来回答
共2个回答
懂视网
时间：2022-04-10 19:59
requests
from lxml import etree
from fake_useragent import UserAgent
import pymongo
class QiShuSpider(object):
def __init__(self):
self.base_url="https://www.qisuu.la/soft/sort01/"
self.headers={
"User-Agent":UserAgent().random,
"HOST":"www.qisuu.la",
"Referer":"https://www.qisuu.la",
}
def get_index_code(self):
#声明一个变量，记录重连的次数
retry_link_count=0
while True:
try:
response=requests.get(self.base_url,headers=self.headers)
# print(response.text)
except Exception as e:
print("连接奇书网失败，原因是:",e)
print("正在尝试第{}次重连....".format(retry_link_count))
retry_link_count+=1
if retry_link_count>=5:
print("尝试连接次数已经达到五次，停止连接")
break
else:
html_obj=etree.HTML(response.text)
# print(response.text)
#获取option这个标签列表
option_list=html_obj.cssselect("select>option")
return option_list
def get_every_page_code(self):
option_list=self.get_index_code()
for option in option_list:
value=option.get("value")
#拼接每一页的完整地址
base_url="https://www.qisuu.la"+value
print("正在爬取{}链接".format(base_url))
response=requests.get(base_url,headers=self.headers).text
html_obj=etree.HTML(response)
#获取每一本小数所在的a标签的一个列表
a_list=html_obj.cssselect(".listBox li>a")
for a in a_list:
novel_href=a.get("href")
#拼接每一本小说的完整地址
novel_url="https://www.qisuu.la"+novel_href
print("正在爬取链接为{}的小说".format(novel_url))
self.parse_every_novel(novel_url)
def parse_every_novel(self,novel_url):
reponse=requests.get(novel_url,headers=self.headers)
reponse.encoding="utf-8"
html_obj=etree.HTML(reponse.text)
novel_name=html_obj.cssselect(".detail_right>h1")[0].text
clik_num=html_obj.cssselect(".detail_right>ul>li:nth-child(1)")[0].text
novel_size=html_obj.cssselect(".detail_right>ul>li:nth-child(2)")[0].text
novel_type=html_obj.cssselect(".detail_right>ul>li:nth-child(3)")[0].text
update_time = html_obj.cssselect(".detail_right>ul>li:nth-child(4)")[0].text
novel_status = html_obj.cssselect(".detail_right>ul>li:nth-child(5)")[0].text
novel_author = html_obj.cssselect(".detail_right>ul>li:nth-child(6)")[0].text
novel_run_envir=html_obj.cssselect(".detail_right>ul>li:nth-child(7)")[0].text
novel_lasted_chapter=html_obj.cssselect(".detail_right>ul>li:nth-child(8)>a")[0].text
dict_novel={"小说名称":novel_name,"点击次数":clik_num,"小说大小":novel_size,"小说类型":novel_type,"更新时间":update_time,"小说状态":novel_status,"小说作者":novel_author,"小说运行环境":novel_run_envir,"小说最新章节":novel_lasted_chapter}
collection.insert_one(dict_novel)
def start_spider(self):
self.get_every_page_code()
if __name__ == ‘__main__‘:
client = pymongo.MongoClient(host="localhost", port=27017)
db = client.novel
collection = db.novel
spider=QiShuSpider()
spider.start_spider()
使用lxml的css选择器用法爬取奇书网并保存到mongoDB中
标签：环境 imp soft www. exce ide link 记录 pymongo
热心网友
时间：2022-04-10 17:07
使用的是 lxml.etree.XML(xml字符串), etree.fromstring(xml字符串)也可以
import lxml.etree
import urllib.request
from lxml.etree import *
str_url = ''
request = urllib.request.Request(str_url)
xml_text = urllib.request.urlopen(request).read()
root = lxml.etree.XML(xml_text) # xml_text 为xml纯文本文件
root 为lxml.etree._Element 对象，含有多个函数
root 含有find，findall， xpath，get，getchildren函数。
