爬虫笔记

import urllib2
import json
import cookielib


def urllib2_request(url, method="GET", cookie="", headers={}, data=None):
    """
    :param url: 要请求的url
    :param cookie: 请求方式，GET、POST、DELETE、PUT..
    :param cookie: 要传入的cookie，cookie= 'k1=v1;k1=v2'
    :param headers: 发送数据时携带的请求头，headers = {'ContentType':'application/json; charset=UTF-8'}
    :param data: 要发送的数据GET方式需要传入参数，data={'d1': 'v1'}
    :return: 返回元祖，响应的字符串内容 和 cookiejar对象
    对于cookiejar对象，可以使用for循环访问：
        for item in cookiejar:
            print item.name,item.value
    """
    if data:
        data = json.dumps(data)

    cookie_jar = cookielib.CookieJar()
    handler = urllib2.HTTPCookieProcessor(cookie_jar)
    opener = urllib2.build_opener(handler)
    opener.addheaders.append(['Cookie', 'k1=v1;k1=v2'])
    request = urllib2.Request(url=url, data=data, headers=headers)
    request.get_method = lambda: method

    response = opener.open(request)
    origin = response.read()

    return origin, cookie_jar


# GET
result = urllib2_request('http://127.0.0.1:8001/index/', method="GET")

# POST
result = urllib2_request('http://127.0.0.1:8001/index/',  method="POST", data= {'k1': 'v1'})

# PUT
result = urllib2_request('http://127.0.0.1:8001/index/',  method="PUT", data= {'k1': 'v1'})

封装urllib请求




import requests
 
ret = requests.get('https://github.com/timeline.json')
 
print ret.url
print ret.text
 
 
 
# 2、有参数实例
 
import requests
 
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.get("http://httpbin.org/get", params=payload)
 
print ret.url
print ret.text




import requests
 
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.post("http://httpbin.org/post", data=payload)
 
print ret.text
 
 
# 2、发送请求头和数据实例
 
import requests
import json
 
url = 'https://api.github.com/some/endpoint'
payload = {'some': 'data'}
headers = {'content-type': 'application/json'}
 
ret = requests.post(url, data=json.dumps(payload), headers=headers)
 
print ret.text
print ret.cookies





requests.get(url, params=None, **kwargs)
requests.post(url, data=None, json=None, **kwargs)
requests.put(url, data=None, **kwargs)
requests.head(url, **kwargs)
requests.delete(url, **kwargs)
requests.patch(url, data=None, **kwargs)
requests.options(url, **kwargs)
 
# 以上方法均是在此方法的基础上构建
requests.request(method, url, **kwargs)



def request(method, url, **kwargs):
    """Constructs and sends a :class:`Request <Request>`.

    :param method: method for the new :class:`Request` object.
    :param url: URL for the new :class:`Request` object.
    :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.
    :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
    :param json: (optional) json data to send in the body of the :class:`Request`.
    :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
    :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
    :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': ('filename', fileobj)}``) for multipart encoding upload.
    :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
    :param timeout: (optional) How long to wait for the server to send data
        before giving up, as a float, or a :ref:`(connect timeout, read
        timeout) <timeouts>` tuple.
    :type timeout: float or tuple
    :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
    :type allow_redirects: bool
    :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
    :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.
    :param stream: (optional) if ``False``, the response content will be immediately downloaded.
    :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response

    Usage::

      >>> import requests
      >>> req = requests.request('GET', 'http://httpbin.org/get')
      <Response [200]>
    """

    # By using the 'with' statement we are sure the session is closed, thus we
    # avoid leaving sockets open which can trigger a ResourceWarning in some
    # cases, and look like a memory leak in others.
    with sessions.Session() as session:
        return session.request(method=method, url=url, **kwargs)

更多参数




# -*- coding:utf-8 -*- 
import requests
import time
import hashlib


def _password(pwd):
    ha = hashlib.md5()
    ha.update(pwd)
    return ha.hexdigest()

def login():
    
    login_dict = {
        'username': "用户名",
        'pwd': _password("密码"),
        'imgcode': "",
        'f': 'json'
    }

    login_res = requests.post(
        url= "https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN",
        data=login_dict,
        headers={'Referer': 'https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN'})

    # 登陆成功之后获取服务器响应的cookie
    resp_cookies_dict = login_res.cookies.get_dict()
    # 登陆成功后，获取服务器响应的内容
    resp_text = login_res.text
    # 登陆成功后，获取token
    token = re.findall(".*token=(d+)", resp_text)[0]

    print resp_text
    print token
    print resp_cookies_dict

login()

登陆代码


# -*- coding:utf-8 -*- 
import requests
import time
import hashlib
import json
import re

LOGIN_COOKIES_DICT = {}

def _password(pwd):
    ha = hashlib.md5()
    ha.update(pwd)
    return ha.hexdigest()

def login():
    
    login_dict = {
        'username': "用户名",
        'pwd': _password("密码"),
        'imgcode': "",
        'f': 'json'
    }

    login_res = requests.post(
        url= "https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN",
        data=login_dict,
        headers={'Referer': 'https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN'})

    # 登陆成功之后获取服务器响应的cookie
    resp_cookies_dict = login_res.cookies.get_dict()
    # 登陆成功后，获取服务器响应的内容
    resp_text = login_res.text
    # 登陆成功后，获取token
    token = re.findall(".*token=(d+)", resp_text)[0]

    return {'token': token, 'cookies': resp_cookies_dict}


def standard_user_list(content):
    content = re.sub('s*', '', content)
    content = re.sub('
*', '', content)
    data = re.findall("""cgiData=(.*);seajs""", content)[0]
    data = data.strip()
    while True:
        temp = re.split('({)(w+)(:)', data, 1)
        if len(temp) == 5:
            temp[2] = '"' + temp[2] + '"'
            data = ''.join(temp)
        else:
            break

    while True:
        temp = re.split('(,)(w+)(:)', data, 1)
        if len(temp) == 5:
            temp[2] = '"' + temp[2] + '"'
            data = ''.join(temp)
        else:
            break

    data = re.sub('*d+', "", data)
    ret = json.loads(data)
    return ret


def get_user_list():

    login_dict = login()
    LOGIN_COOKIES_DICT.update(login_dict)

    login_cookie_dict = login_dict['cookies']
    res_user_list = requests.get(
        url= "https://mp.weixin.qq.com/cgi-bin/user_tag",
        params = {"action": "get_all_data", "lang": "zh_CN", "token": login_dict['token']},
        cookies = login_cookie_dict,
        headers={'Referer': 'https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN'}
    )
    user_info = standard_user_list(res_user_list.text)
    for item in user_info['user_list']:
        print "%s %s " % (item['nick_name'],item['id'],)
    
get_user_list()

代码实现



# -*- coding:utf-8 -*- 
import requests
import time
import hashlib
import json
import re

LOGIN_COOKIES_DICT = {}

def _password(pwd):
    ha = hashlib.md5()
    ha.update(pwd)
    return ha.hexdigest()

def login():
    
    login_dict = {
        'username': "用户名",
        'pwd': _password("密码"),
        'imgcode': "",
        'f': 'json'
    }

    login_res = requests.post(
        url= "https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN",
        data=login_dict,
        headers={'Referer': 'https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN'})

    # 登陆成功之后获取服务器响应的cookie
    resp_cookies_dict = login_res.cookies.get_dict()
    # 登陆成功后，获取服务器响应的内容
    resp_text = login_res.text
    # 登陆成功后，获取token
    token = re.findall(".*token=(d+)", resp_text)[0]

    return {'token': token, 'cookies': resp_cookies_dict}


def standard_user_list(content):
    content = re.sub('s*', '', content)
    content = re.sub('
*', '', content)
    data = re.findall("""cgiData=(.*);seajs""", content)[0]
    data = data.strip()
    while True:
        temp = re.split('({)(w+)(:)', data, 1)
        if len(temp) == 5:
            temp[2] = '"' + temp[2] + '"'
            data = ''.join(temp)
        else:
            break

    while True:
        temp = re.split('(,)(w+)(:)', data, 1)
        if len(temp) == 5:
            temp[2] = '"' + temp[2] + '"'
            data = ''.join(temp)
        else:
            break

    data = re.sub('*d+', "", data)
    ret = json.loads(data)
    return ret


def get_user_list():

    login_dict = login()
    LOGIN_COOKIES_DICT.update(login_dict)

    login_cookie_dict = login_dict['cookies']
    res_user_list = requests.get(
        url= "https://mp.weixin.qq.com/cgi-bin/user_tag",
        params = {"action": "get_all_data", "lang": "zh_CN", "token": login_dict['token']},
        cookies = login_cookie_dict,
        headers={'Referer': 'https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN'}
    )
    user_info = standard_user_list(res_user_list.text)
    for item in user_info['user_list']:
        print "%s %s " % (item['nick_name'],item['id'],)
    

def send_msg(user_fake_id, content='啥也没发'):

    login_dict = LOGIN_COOKIES_DICT
    
    token = login_dict['token']
    login_cookie_dict = login_dict['cookies']

    send_dict = {
        'token': token,
        'lang': "zh_CN",
        'f': 'json',
        'ajax': 1,
        'random': "0.5322618900912392",
        'type': 1,
        'content': content,
        'tofakeid': user_fake_id,
        'imgcode': ''
    }
   
    send_url = "https://mp.weixin.qq.com/cgi-bin/singlesend?t=ajax-response&f=json&token=%s&lang=zh_CN" % (token,)
    message_list = requests.post(
        url=send_url, 
        data=send_dict, 
        cookies=login_cookie_dict, 
        headers={'Referer': 'https://mp.weixin.qq.com/cgi-bin/login?lang=zh_CN'}
    )


get_user_list()
fake_id = raw_input('请输入用户ID:')
content = raw_input('请输入消息内容:')
send_msg(fake_id, content)

发送消息代码


#!/usr/bin/env python
# -*- coding:utf-8 -*-
import scrapy
 
class XiaoHuarSpider(scrapy.spiders.Spider):
    name = "xiaohuar"
    allowed_domains = ["xiaohuar.com"]
    start_urls = [
        "http://www.xiaohuar.com/hua/",
    ]
 
    def parse(self, response):
        # print(response, type(response))
        # from scrapy.http.response.html import HtmlResponse
        # print(response.body_as_unicode())
 
        current_url = response.url
        body = response.body
        unicode_body = response.body_as_unicode()



#!/usr/bin/env python
# -*- coding:utf-8 -*-
import scrapy
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector
import re
import urllib
import os
 
 
class XiaoHuarSpider(scrapy.spiders.Spider):
    name = "xiaohuar"
    allowed_domains = ["xiaohuar.com"]
    start_urls = [
        "http://www.xiaohuar.com/list-1-1.html",
    ]
 
    def parse(self, response):
        # 分析页面
        # 找到页面中符合规则的内容（校花图片），保存
        # 找到所有的a标签，再访问其他a标签，一层一层的搞下去
 
        hxs = HtmlXPathSelector(response)
 
        # 如果url是 http://www.xiaohuar.com/list-1-d+.html
        if re.match('http://www.xiaohuar.com/list-1-d+.html', response.url):
            items = hxs.select('//div[@class="item_list infinite_scroll"]/div')
            for i in range(len(items)):
                src = hxs.select('//div[@class="item_list infinite_scroll"]/div[%d]//div[@class="img"]/a/img/@src' % i).extract()
                name = hxs.select('//div[@class="item_list infinite_scroll"]/div[%d]//div[@class="img"]/span/text()' % i).extract()
                school = hxs.select('//div[@class="item_list infinite_scroll"]/div[%d]//div[@class="img"]/div[@class="btns"]/a/text()' % i).extract()
                if src:
                    ab_src = "http://www.xiaohuar.com" + src[0]
                    file_name = "%s_%s.jpg" % (school[0].encode('utf-8'), name[0].encode('utf-8'))
                    file_path = os.path.join("/Users/wupeiqi/PycharmProjects/beauty/pic", file_name)
                    urllib.urlretrieve(ab_src, file_path)
 
        # 获取所有的url，继续访问，并在其中寻找相同的url
        all_urls = hxs.select('//a/@href').extract()
        for url in all_urls:
            if url.startswith('http://www.xiaohuar.com/list-1-'):
                yield Request(url, callback=self.parse)





#!/usr/bin/env python
# -*- coding:utf-8 -*-

import scrapy
import hashlib
from tutorial.items import JinLuoSiItem
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector


class JinLuoSiSpider(scrapy.spiders.Spider):
    count = 0
    url_set = set()

    name = "jluosi"
    domain = 'http://www.jluosi.com'
    allowed_domains = ["jluosi.com"]

    start_urls = [
        "http://www.jluosi.com:80/ec/goodsDetail.action?jls=QjRDNEIzMzAzOEZFNEE3NQ==",
    ]

    def parse(self, response):
        md5_obj = hashlib.md5()
        md5_obj.update(response.url)
        md5_url = md5_obj.hexdigest()
        if md5_url in JinLuoSiSpider.url_set:
            pass
        else:
            JinLuoSiSpider.url_set.add(md5_url)
            hxs = HtmlXPathSelector(response)
            if response.url.startswith('http://www.jluosi.com:80/ec/goodsDetail.action'):
                item = JinLuoSiItem()
                item['company'] = hxs.select('//div[@class="ShopAddress"]/ul/li[1]/text()').extract()
                item['link'] = hxs.select('//div[@class="ShopAddress"]/ul/li[2]/text()').extract()
                item['qq'] = hxs.select('//div[@class="ShopAddress"]//a/@href').re('.*uin=(?P<qq>d*)&')
                item['address'] = hxs.select('//div[@class="ShopAddress"]/ul/li[4]/text()').extract()

                item['title'] = hxs.select('//h1[@class="goodsDetail_goodsName"]/text()').extract()

                item['unit'] = hxs.select('//table[@class="R_WebDetail_content_tab"]//tr[1]//td[3]/text()').extract()
                product_list = []
                product_tr = hxs.select('//table[@class="R_WebDetail_content_tab"]//tr')
                for i in range(2,len(product_tr)):
                    temp = {
                        'standard':hxs.select('//table[@class="R_WebDetail_content_tab"]//tr[%d]//td[2]/text()' %i).extract()[0].strip(),
                        'price':hxs.select('//table[@class="R_WebDetail_content_tab"]//tr[%d]//td[3]/text()' %i).extract()[0].strip(),
                    }
                    product_list.append(temp)

                item['product_list'] = product_list
                yield item

            current_page_urls = hxs.select('//a/@href').extract()
            for i in range(len(current_page_urls)):
                url = current_page_urls[i]
                if url.startswith('http://www.jluosi.com'):
                    url_ab = url
                    yield Request(url_ab, callback=self.parse)

选择器规则Demo




# -*- coding: utf-8 -*-
 
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
 
import scrapy
 
class JieYiCaiItem(scrapy.Item):
 
    company = scrapy.Field()
    title = scrapy.Field()
    qq = scrapy.Field()
    info = scrapy.Field()
    more = scrapy.Field()



#!/usr/bin/env python
# -*- coding:utf-8 -*-

import scrapy
import hashlib
from beauty.items import JieYiCaiItem
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor


class JieYiCaiSpider(scrapy.spiders.Spider):
    count = 0
    url_set = set()

    name = "jieyicai"
    domain = 'http://www.jieyicai.com'
    allowed_domains = ["jieyicai.com"]

    start_urls = [
        "http://www.jieyicai.com",
    ]

    rules = [
        #下面是符合规则的网址,但是不抓取内容,只是提取该页的链接(这里网址是虚构的,实际使用时请替换)
        #Rule(SgmlLinkExtractor(allow=(r'http://test_url/test?page_index=d+'))),
        #下面是符合规则的网址,提取内容,(这里网址是虚构的,实际使用时请替换)
        #Rule(LinkExtractor(allow=(r'http://www.jieyicai.com/Product/Detail.aspx?pid=d+')), callback="parse"),
    ]

    def parse(self, response):
        md5_obj = hashlib.md5()
        md5_obj.update(response.url)
        md5_url = md5_obj.hexdigest()
        if md5_url in JieYiCaiSpider.url_set:
            pass
        else:
            JieYiCaiSpider.url_set.add(md5_url)
            
            hxs = HtmlXPathSelector(response)
            if response.url.startswith('http://www.jieyicai.com/Product/Detail.aspx'):
                item = JieYiCaiItem()
                item['company'] = hxs.select('//span[@class="username g-fs-14"]/text()').extract()
                item['qq'] = hxs.select('//span[@class="g-left bor1qq"]/a/@href').re('.*uin=(?P<qq>d*)&')
                item['info'] = hxs.select('//div[@class="padd20 bor1 comard"]/text()').extract()
                item['more'] = hxs.select('//li[@class="style4"]/a/@href').extract()
                item['title'] = hxs.select('//div[@class="g-left prodetail-text"]/h2/text()').extract()
                yield item

            current_page_urls = hxs.select('//a/@href').extract()
            for i in range(len(current_page_urls)):
                url = current_page_urls[i]
                if url.startswith('/'):
                    url_ab = JieYiCaiSpider.domain + url
                    yield Request(url_ab, callback=self.parse)

spider


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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

import json
from twisted.enterprise import adbapi
import MySQLdb.cursors
import re

mobile_re = re.compile(r'(13[0-9]|15[012356789]|17[678]|18[0-9]|14[57])[0-9]{8}')
phone_re = re.compile(r'(d+-d+|d+)')

class JsonPipeline(object):

    def __init__(self):
        self.file = open('/Users/wupeiqi/PycharmProjects/beauty/beauty/jieyicai.json', 'wb')


    def process_item(self, item, spider):
        line = "%s  %s
" % (item['company'][0].encode('utf-8'), item['title'][0].encode('utf-8'))
        self.file.write(line)
        return item

class DBPipeline(object):

    def __init__(self):
        self.db_pool = adbapi.ConnectionPool('MySQLdb',
                                             db='DbCenter',
                                             user='root',
                                             passwd='123',
                                             cursorclass=MySQLdb.cursors.DictCursor,
                                             use_unicode=True)

    def process_item(self, item, spider):
        query = self.db_pool.runInteraction(self._conditional_insert, item)
        query.addErrback(self.handle_error)
        return item

    def _conditional_insert(self, tx, item):
        tx.execute("select nid from company where company = %s", (item['company'][0], ))
        result = tx.fetchone()
        if result:
            pass
        else:
            phone_obj = phone_re.search(item['info'][0].strip())
            phone = phone_obj.group() if phone_obj else ' '

            mobile_obj = mobile_re.search(item['info'][1].strip())
            mobile = mobile_obj.group() if mobile_obj else ' '

            values = (
                item['company'][0],
                item['qq'][0],
                phone,
                mobile,
                item['info'][2].strip(),
                item['more'][0])
            tx.execute("insert into company(company,qq,phone,mobile,address,more) values(%s,%s,%s,%s,%s,%s)", values)

    def handle_error(self, e):
        print 'error',e

pipelines



ITEM_PIPELINES = {
    'beauty.pipelines.DBPipeline': 300,
    'beauty.pipelines.JsonPipeline': 100,
}