python爬虫（二）

针对《用Python写网络爬虫》的第二章，该章主要讲述了如何从网页中抽取数据。

1. 现讲述一下正则匹配数据的方法：

import urllib2
import re


def scrape(html):
    area = re.findall('<tr id="places_area__row">.*?<td\s*class=["\']w2p_fw["\']>(.*?)</td>', html)[0]
    return area


if __name__ == '__main__':
    html = urllib2.urlopen('http://example.webscraping.com/places/default/view/United-Kingdom-239').read()
    print scrape(html)

#244,820 square kilometres

2. 使用 beautiful-soup匹配数据：

安装beautifulsoup的方法： pip install beautifulsoup4

示例代码：

#exmple: https://bitbucket.org/wswp/code/src/9e6b82b47087c2ada0e9fdf4f5e037e151975f0f/chapter02/bs_example.py?at=default&fileviewer=file-view-default


import urllib2
from bs4 import BeautifulSoup

def scrape(html):
    soup = BeautifulSoup(html, 'html.parser') 
    tr = soup.find(attrs={'id':'places_area__row'}) # locate the area row
    # 'class' is a special python attribute so instead 'class_' is used
    td = tr.find(attrs={'class':'w2p_fw'})  # locate the area tag
    area = td.text  # extract the area contents from this tag
    return area

if __name__ == '__main__':
    html = urllib2.urlopen('http://example.webscraping.com/places/default/view/United-Kingdom-239').read()
    print scrape(html)

#244,820 square kilometres

3. lxml + cssselect 匹配数据：

安装lxml的方法：配置pip源，pip install lxml

安装cssselect的方法： pip install cssselect 

# -*- coding: utf-8 -*-

import urllib2
from lxml import html


def scrape(htmlContent):
    tree = html.fromstring(htmlContent)
    td = tree.cssselect('tr#places_area__row > td.w2p_fw')[0]
    area = td.text_content()
    #244,820 square kilometres
    return area

if __name__ == '__main__':
    htmlContent = urllib2.urlopen('http://example.webscraping.com/places/default/view/United-Kingdom-239').read()
    print scrape(htmlContent)

cssselect对css3标签支持的情况参照：

https://cssselect.readthedocs.io/en/latest/#user-api

4. regex, beautifulsoup, lxml三种方式的性能对比

抓取同一个地址: 

http://example.webscraping.com/places/default/view/United-Kingdom-239

执行10次，结果如下：

代码部分：

# -*- coding: utf-8 -*-

import csv
import time
import urllib2
import re
import timeit
from bs4 import BeautifulSoup
import lxml.html

#FIELDS = ('area', 'population', 'iso', 'country', 'capital', 'continent', 'tld', 'currency_code', 'currency_name', 'phone', 'postal_code_format', 'postal_code_regex', 'languages', 'neighbours')
FIELDS = ('area', 'population', 'iso')

def regex_scraper(html):
    results = {}
    for field in FIELDS:
        results[field] = re.search('<tr id="places_{}__row">.*?<td class="w2p_fw">(.*?)</td>'.format(field), html).groups()[0]
    return results


def beautiful_soup_scraper(html):
    soup = BeautifulSoup(html, 'html.parser') 
    results = {}
    for field in FIELDS:
        results[field] = soup.find('table').find('tr', id='places_{}__row'.format(field)).find('td', class_='w2p_fw').text
    return results


def lxml_scraper(html):
    tree = lxml.html.fromstring(html)
    results = {}
    for field in FIELDS:
        results[field] = tree.cssselect('table > tr#places_{}__row > td.w2p_fw'.format(field))[0].text_content()
    return results


def main():
    times = {}
    html = urllib2.urlopen('http://example.webscraping.com/places/default/view/United-Kingdom-239').read()
    NUM_ITERATIONS = 10 # number of times to test each scraper
    for name, scraper in ('Regular expressions', regex_scraper), ('Beautiful Soup', beautiful_soup_scraper), ('Lxml', lxml_scraper):
        times[name] = []
        # record start time of scrape
        start = time.time()
        for i in range(NUM_ITERATIONS):
            if scraper == regex_scraper:
                # the regular expression module will cache results
                # so need to purge this cache for meaningful timings
                re.purge() 
            result = scraper(html)

            # check scraped result is as expected
            assert(result['area'] == '244,820 square kilometres')
            times[name].append(time.time() - start)
        # record end time of scrape and output the total
        end = time.time()
        print '{}: {:.2f} seconds'.format(name, end - start)

    writer = csv.writer(open('times.csv', 'w'))
    header = sorted(times.keys())
    writer.writerow(header)
    for row in zip(*[times[scraper] for scraper in header]):
        writer.writerow(row)


if __name__ == '__main__':
    main()

通过以上结果可以总结出以上抓取方法的优缺点：

抓取方法	性能	使用难度	安装难度
正则表达式	快	困难	简单（内置模块）
Beautiful Soup	慢	简单	简单（纯python）
Lxml	快	简单	相对困难

通常情况下，lxml是抓取数据的最好选择，因为该方法既快速又健壮，而正则和Beautiful Soup只在特定场景下有用。

5. 为链接爬虫添加抓取回调

link_crawler.py： 

import re
import urlparse
import urllib2
import time
from datetime import datetime
import robotparser
import Queue


def link_crawler(seed_url, link_regex=None, delay=5, max_depth=-1, max_urls=-1, headers=None, user_agent='wswp', proxy=None, num_retries=1, scrape_callback=None):
    """Crawl from the given seed URL following links matched by link_regex
    """
    # the queue of URL's that still need to be crawled
    crawl_queue = [seed_url]
    # the URL's that have been seen and at what depth
    seen = {seed_url: 0}
    # track how many URL's have been downloaded
    num_urls = 0
    rp = get_robots(seed_url)
    throttle = Throttle(delay)
    headers = headers or {}
    if user_agent:
        headers['User-agent'] = user_agent

    while crawl_queue:
        url = crawl_queue.pop()
        depth = seen[url]
        # check url passes robots.txt restrictions
        if rp.can_fetch(user_agent, url):
            throttle.wait(url)
            html = download(url, headers, proxy=proxy, num_retries=num_retries)
            links = []
            if scrape_callback:
                links.extend(scrape_callback(url, html) or [])

            if depth != max_depth:
                # can still crawl further
                temp_links = get_links(html)
                if link_regex:
                    # filter for links matching our regular expression
                    links.extend(link for link in temp_links if re.match(link_regex, link))

                for link in links:
                    link = normalize(seed_url, link)
                    # check whether already crawled this link
                    if link not in seen:
                        seen[link] = depth + 1
                        # check link is within same domain
                        if same_domain(seed_url, link):
                            # success! add this new link to queue
                            crawl_queue.append(link)

            # check whether have reached downloaded maximum
            num_urls += 1
            if num_urls == max_urls:
                break
        else:
            print 'Blocked by robots.txt:', url


class Throttle:
    """Throttle downloading by sleeping between requests to same domain
    """
    def __init__(self, delay):
        # amount of delay between downloads for each domain
        self.delay = delay
        # timestamp of when a domain was last accessed
        self.domains = {}
        
    def wait(self, url):
        """Delay if have accessed this domain recently
        """
        domain = urlparse.urlsplit(url).netloc
        last_accessed = self.domains.get(domain)
        if self.delay > 0 and last_accessed is not None:
            sleep_secs = self.delay - (datetime.now() - last_accessed).seconds
            if sleep_secs > 0:
                time.sleep(sleep_secs)
        self.domains[domain] = datetime.now()



def download(url, headers, proxy, num_retries, data=None):
    print 'Downloading:', url
    request = urllib2.Request(url, data, headers)
    opener = urllib2.build_opener()
    if proxy:
        proxy_params = {urlparse.urlparse(url).scheme: proxy}
        opener.add_handler(urllib2.ProxyHandler(proxy_params))
    try:
        response = opener.open(request)
        html = response.read()
        code = response.code
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = ''
        if hasattr(e, 'code'):
            code = e.errno  
            if num_retries > 0 and 500 <= code < 600:
                # retry 5XX HTTP errors
                html = download(url, headers, proxy, num_retries-1, data)
        else:
            code = None
    return html


def normalize(seed_url, link):
    """Normalize this URL by removing hash and adding domain
    """
    link, _ = urlparse.urldefrag(link) # remove hash to avoid duplicates
    return urlparse.urljoin(seed_url, link)


def same_domain(url1, url2):
    """Return True if both URL's belong to same domain
    """
    return urlparse.urlparse(url1).netloc == urlparse.urlparse(url2).netloc


def get_robots(url):
    """Initialize robots parser for this domain
    """
    rp = robotparser.RobotFileParser()
    rp.set_url(urlparse.urljoin(url, '/robots.txt'))
    rp.read()
    return rp
        


def get_links(html):
    """Return a list of links from html 
    """
    # a regular expression to extract all links from the webpage
    webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE)
    # list of all links from the webpage
    return webpage_regex.findall(html)

回调函数：

# -*- coding: utf-8 -*-

import csv
import re
import urlparse
import lxml.html
from link_crawler import link_crawler


class ScrapeCallback:
    def __init__(self):
        self.writer = csv.writer(open('countries.csv', 'w'))
        self.fields = ('area', 'population', 'iso', 'country', 'capital', 'continent', 'tld', 'currency_code', 'currency_name', 'phone', 'postal_code_format', 'postal_code_regex', 'languages', 'neighbours')
        self.writer.writerow(self.fields)

    def __call__(self, url, html):
        if re.search('/places/default/view/', url):
            tree = lxml.html.fromstring(html)
            row = []
            for field in self.fields:
                row.append(tree.cssselect('table > tr#places_{}__row > td.w2p_fw'.format(field))[0].text_content())
            print row
            self.writer.writerow(row)

if __name__ == '__main__':
    link_crawler('http://example.webscraping.com/places/default/', link_regex='/places/default/(index|view)', max_depth=1, num_retries=3, scrape_callback=ScrapeCallback())

以上代码的执行结果：

以上就是《用Python写网络爬虫》的第二章的概括总结了。