解析网页速度比较（BeautifulSoup、PyQuery、lxml、正则）

==== Python version: 3.6.7 (v3.6.7:6ec5cf24b7, Oct 20 2018, 03:02:14) 
[GCC 4.2.1 Compatible Apple LLVM 6.0 (clang-600.0.57)] =====

==== Total trials: 10000 =====
bs4 total time: 7.7
pq total time: 0.9
lxml (cssselect) total time: 0.9
lxml (xpath) total time: 0.6
regex total time: 1.0 (doesn't find all p)

import re
import sys
import time
import requests
from lxml.html import fromstring
from pyquery import PyQuery as pq
from bs4 import BeautifulSoup as bs

def Timer():
    a = time.time()
    while True:
        c = time.time()
        yield time.time()-a
        a = c
timer = Timer()
url = "http://www.python.org/"
html = requests.get(url).text
num = 10000
print ('\n==== Python version: %s =====' %sys.version)
print ('\n==== Total trials: %s =====' %num)
next(timer)
soup = bs(html, 'lxml')
for x in range(num):
    paragraphs = soup.findAll('p')
t = next(timer)
print ('bs4 total time: %.1f' %t)
d = pq(html)
for x in range(num):
    paragraphs = d('p')
t = next(timer)
print ('pq total time: %.1f' %t)
tree = fromstring(html)
for x in range(num):
    paragraphs = tree.cssselect('p')
t = next(timer)
print ('lxml (cssselect) total time: %.1f' %t)
tree = fromstring(html)
for x in range(num):
    paragraphs = tree.xpath('.//p')
t = next(timer)
print ('lxml (xpath) total time: %.1f' %t)
for x in range(num):
    paragraphs = re.findall('<[p ]>.*?</p>', html)
t = next(timer)
print ('regex total time: %.1f (doesn\'t find all p)\n' %t)

from pyquery import PyQuery as pq

url = 'https://www.feixiaohao.com/currencies/bitcoin/'
headers = {
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
                          '(KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
        }
doc = pq(url=url, headers=headers, method='get')

# 也支持发送表单数据
# pq(your_url, {'q': 'foo'}, method='post', verify=True)

# btc价格
btc_price = doc('.mainPrice span.convert').text()
print(btc_price)

# btc logo
btc_logo = doc('img.coinLogo').attr('src')
print(btc_logo)

from pyquery import PyQuery as pq

html = '''
<div>
    <ul>
         <li class="item-0">first item</li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
         <li class="item-1 active"><a href="link4.html">fourth item</a></li>
         <li class="item-0"><a href="link5.html">fifth item</a></li>
    </ul>
</div>
'''

doc = pq(html)
# doc = pq(filename='demo.html')

# 使用eq可以按次序选择
print(doc('li').eq(1))

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2019-01-30 16:22:03
# Project: imdb

from pyspider.libs.base_handler import *


class Handler(BaseHandler):
    crawl_config = {
    }

    @every(minutes=5)
    def on_start(self):
        self.crawl('https://www.imdb.com/chart/top', callback=self.index_page)

    @config(age=10 * 24 * 60 * 60)
    def index_page(self, response):
        for each in response.doc('.titleColumn > a').items():
            self.crawl(each.attr.href, callback=self.detail_page, fetch_type='js')

    @config(priority=2)
    def detail_page(self, response):
        return {            
            "title": response.doc('h1').text(),
            "voters": response.doc('[itemprop="aggregateRating"] > a > span').text(),
            "score": response.doc('strong > span').text()
        }

    # 需要再init中定义mongoclient
    def on_result(self, result):
        self.mongo.insert_result(result)
        super(Handler, self).on_result(result)