整理了一下网易云歌曲评论抓取、分析好友信息抓取、淘宝宝贝抓取、今日头条美图抓取的一些代码
抓取网易云评论
进入歌曲界面：
http://music.163.com/#/song?id=453185824
找到如下的数据源：
贴一段Lyrichu的代码：
(运行环境为P2.7)
# -*- coding: utf-8 -*-# @Time : 2017/3/28 8:46# @Author : Lyrichu# @Email : [email protected]# @File : NetCloud_spider3.py‘‘‘@Description:网易云音乐评论爬虫，可以完整爬取整个评论部分参考了@平胸小仙女的文章(地址:https://www.zhihu.com/question/36081767)post加密部分也给出了，可以参考原帖：作者：平胸小仙女链接：https://www.zhihu.com/question/36081767/answer/140287795来源：知乎‘‘‘from Crypto.Cipher import AESimport base64import requestsimport jsonimport codecsimport time
# 头部信息headers = { ‘Host‘:"music.163.com", ‘Accept-Language‘:"zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3", ‘Accept-Encoding‘:"gzip, deflate", ‘Content-Type‘:"application/x-www-form-urlencoded", ‘Cookie‘:"_ntes_nnid=754361b04b121e078dee797cdb30e0fd,1486026808627; _ntes_nuid=754361b04b121e078dee797cdb30e0fd; JSESSIONID-WYYY=yfqt9ofhY%5CIYNkXW71TqY5OtSZyjE%2FoswGgtl4dMv3Oa7%5CQ50T%2FVaee%2FMSsCifHE0TGtRMYhSPpr20i%5CRO%2BO%2B9pbbJnrUvGzkibhNqw3Tlgn%5Coil%2FrW7zFZZWSA3K9gD77MPSVH6fnv5hIT8ms70MNB3CxK5r3ecj3tFMlWFbFOZmGw%5C%3A1490677541180; _iuqxldmzr_=32; vjuids=c8ca7976.15a029d006a.0.51373751e63af8; vjlast=1486102528.1490172479.21; __gads=ID=a9eed5e3cae4d252:T=1486102537:S=ALNI_Mb5XX2vlkjsiU5cIy91-ToUDoFxIw; vinfo_n_f_l_n3=411a2def7f75a62e.1.1.1486349441669.1486349607905.1490173828142; [email protected]|1489375076|1|study|00&99|null&null&null#hub&420100#10#0#0|155439&1|study_client|[email protected]; NTES_CMT_USER_INFO=84794134%7Cm155****4439%7Chttps%3A%2F%2Fsimg.ws.126.net%2Fe%2Fimg5.cache.netease.com%2Ftie%2Fimages%2Fyun%2Fphoto_default_62.png.39x39.100.jpg%7Cfalse%7CbTE1NTI3NTk0NDM5QDE2My5jb20%3D; usertrack=c+5+hljHgU0T1FDmA66MAg==; Province=027; City=027; _ga=GA1.2.1549851014.1489469781; __utma=94650624.1549851014.1489469781.1490664577.1490672820.8; __utmc=94650624; __utmz=94650624.1490661822.6.2.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; playerid=81568911; __utmb=94650624.23.10.1490672820", ‘Connection‘:"keep-alive", ‘Referer‘:‘http://music.163.com/‘}# 设置代理服务器proxies= { ‘http:‘:‘http://121.232.146.184‘, ‘https:‘:‘https://144.255.48.197‘ }
# offset的取值为:(评论页数-1)*20,total第一页为true，其余页为false# first_param = ‘{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}‘ # 第一个参数second_param = "010001" # 第二个参数# 第三个参数third_param = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7"# 第四个参数forth_param = "0CoJUm6Qyw8W8jud"
# 获取参数def get_params(page): # page为传入页数 iv = "0102030405060708" first_key = forth_param second_key = 16 * ‘F‘ if(page == 1): # 如果为第一页 first_param = ‘{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}‘ h_encText = AES_encrypt(first_param, first_key, iv) else: offset = str((page-1)*20) first_param = ‘{rid:"", offset:"%s", total:"%s", limit:"20", csrf_token:""}‘ %(offset,‘false‘) h_encText = AES_encrypt(first_param, first_key, iv) h_encText = AES_encrypt(h_encText, second_key, iv) return h_encText
# 获取 encSecKeydef get_encSecKey(): encSecKey = "257348aecb5e556c066de214e531faadd1c55d814f9be95fd06d6bff9f4c7a41f831f6394d5a3fd2e3881736d94a02ca919d952872e7d0a50ebfa1769a7a62d512f5f1ca21aec60bc3819a9c3ffca5eca9a0dba6d6f7249b06f5965ecfff3695b54e1c28f3f624750ed39e7de08fc8493242e26dbc4484a01c76f739e135637c" return encSecKey
# 解密过程def AES_encrypt(text, key, iv): pad = 16 - len(text) % 16 text = text + pad * chr(pad) encryptor = AES.new(key, AES.MODE_CBC, iv) encrypt_text = encryptor.encrypt(text) encrypt_text = base64.b64encode(encrypt_text) return encrypt_text
# 获得评论json数据def get_json(url, params, encSecKey): data = { "params": params, "encSecKey": encSecKey } response = requests.post(url, headers=headers, data=data,proxies = proxies) return response.content
# 抓取热门评论，返回热评列表def get_hot_comments(url): hot_comments_list = [] hot_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n") params = get_params(1) # 第一页 encSecKey = get_encSecKey() json_text = get_json(url,params,encSecKey) json_dict = json.loads(json_text) hot_comments = json_dict[‘hotComments‘] # 热门评论 print("共有%d条热门评论!" % len(hot_comments)) for item in hot_comments: comment = item[‘content‘] # 评论内容 likedCount = item[‘likedCount‘] # 点赞总数 comment_time = item[‘time‘] # 评论时间(时间戳) userID = item[‘user‘][‘userID‘] # 评论者id nickname = item[‘user‘][‘nickname‘] # 昵称 avatarUrl = item[‘user‘][‘avatarUrl‘] # 头像地址 comment_info = userID + " " + nickname + " " + avatarUrl + " " + comment_time + " " + likedCount + " " + comment + u"\n" hot_comments_list.append(comment_info) return hot_comments_list
# 抓取某一首歌的全部评论def get_all_comments(url): all_comments_list = [] # 存放所有评论 all_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n") # 头部信息 params = get_params(1) encSecKey = get_encSecKey() json_text = get_json(url,params,encSecKey) json_dict = json.loads(json_text) comments_num = int(json_dict[‘total‘]) if(comments_num % 20 == 0): page = comments_num / 20 else: page = int(comments_num / 20) + 1 print("共有%d页评论!" % page) for i in range(page): # 逐页抓取 params = get_params(i+1) encSecKey = get_encSecKey() json_text = get_json(url,params,encSecKey) json_dict = json.loads(json_text) if i == 0: print("共有%d条评论!" % comments_num) # 全部评论总数 for item in json_dict[‘comments‘]: comment = item[‘content‘] # 评论内容 likedCount = item[‘likedCount‘] # 点赞总数 comment_time = item[‘time‘] # 评论时间(时间戳) userID = item[‘user‘][‘userId‘] # 评论者id nickname = item[‘user‘][‘nickname‘] # 昵称 avatarUrl = item[‘user‘][‘avatarUrl‘] # 头像地址 comment_info = unicode(userID) + u" " + nickname + u" " + avatarUrl + u" " + unicode(comment_time) + u" " + unicode(likedCount) + u" " + comment + u"\n" all_comments_list.append(comment_info) print("第%d页抓取完毕!" % (i+1)) return all_comments_list
# 将评论写入文本文件def save_to_file(list,filename): with codecs.open(filename,‘a‘,encoding=‘utf-8‘) as f: f.writelines(list) print("写入文件成功!")
if __name__ == "__main__": start_time = time.time() # 开始时间 url = "http://music.163.com/weapi/v1/resource/comments/R_SO_4_453185824?csrf_token=" filename = u"On_My_Way.txt" all_comments_list = get_all_comments(url) save_to_file(all_comments_list,filename) end_time = time.time() #结束时间 print("程序耗时%f秒." % (end_time - start_time))
其中AES需要安装pycrypto库，在安装时报错，点击more，可以找到需要安装的C类库即可（直接复制相应的网址，下载并安装即可，好像是VCForPython27.msi）
结果如下：
代码文件：
参考：
http://www.jianshu.com/p/50d99bd7ed62
https://toutiao.io/posts/ewjm4f/preview
******************************?******************************
抓取微信好友信息
代码如下：
#!/usr/bin/env python# encoding=utf-8from __future__ import print_function
import osimport requestsimport reimport timeimport xml.dom.minidomimport jsonimport sysimport mathimport subprocessimport sslimport threadingimport urllib, urllib2
DEBUG = False
MAX_GROUP_NUM = 2 # 每组人数INTERFACE_CALLING_INTERVAL = 5 # 接口调用时间间隔, 间隔太短容易出现"操作太频繁", 会被限制操作半小时左右MAX_PROGRESS_LEN = 50
QRImagePath = os.path.join(os.getcwd(), ‘qrcode.jpg‘)
tip = 0uuid = ‘‘
base_uri = ‘‘redirect_uri = ‘‘push_uri = ‘‘
skey = ‘‘wxsid = ‘‘wxuin = ‘‘pass_ticket = ‘‘deviceId = ‘e000000000000000‘
BaseRequest = {}
ContactList = []My = []SyncKey = []
try: xrange range = xrangeexcept: # python 3 pass
def responseState(func, BaseResponse): ErrMsg = BaseResponse[‘ErrMsg‘] Ret = BaseResponse[‘Ret‘] if DEBUG or Ret != 0: print(‘func: %s, Ret: %d, ErrMsg: %s‘ % (func, Ret, ErrMsg))
if Ret != 0: return False
return True
def getUUID(): global uuid
url = ‘https://login.weixin.qq.com/jslogin‘ params = { ‘appid‘: ‘wx782c26e4c19acffb‘, ‘fun‘: ‘new‘, ‘lang‘: ‘zh_CN‘, ‘_‘: int(time.time()), }
r = myRequests.get(url=url, params=params) r.encoding = ‘utf-8‘ data = r.text
# print(data)
# window.QRLogin.code = 200; window.QRLogin.uuid = "oZwt_bFfRg=="; regx = r‘window.QRLogin.code = (\d+); window.QRLogin.uuid = "(\S+?)"‘ pm = re.search(regx, data)
code = pm.group(1) uuid = pm.group(2)
if code == ‘200‘: return True
return False
def showQRImage(): global tip
url = ‘https://login.weixin.qq.com/qrcode/‘ + uuid params = { ‘t‘: ‘webwx‘, ‘_‘: int(time.time()), }
r = myRequests.get(url=url, params=params) tip = 1
f = open(QRImagePath, ‘wb+‘) f.write(r.content) f.close() time.sleep(1)
if sys.platform.find(‘darwin‘) >= 0: subprocess.call([‘open‘, QRImagePath]) else: os.startfile(QRImagePath) print(‘请使用微信扫描二维码以登录‘)
def waitForLogin(): global tip, base_uri, redirect_uri, push_uri
url = ‘https://login.weixin.qq.com/cgi-bin/mmwebwx-bin/login?tip=%s&uuid=%s&_=%s‘ % ( tip, uuid, int(time.time()))
r = myRequests.get(url=url) r.encoding = ‘utf-8‘ data = r.text
# print(data)
# window.code=500; regx = r‘window.code=(\d+);‘ pm = re.search(regx, data)
code = pm.group(1)
if code == ‘201‘: # 已扫描 print(‘成功扫描,请在手机上点击确认以登录‘) tip = 0 elif code == ‘200‘: # 已登录 print(‘正在登录...‘) regx = r‘window.redirect_uri="(\S+?)";‘ pm = re.search(regx, data) redirect_uri = pm.group(1) + ‘&fun=new‘ base_uri = redirect_uri[:redirect_uri.rfind(‘/‘)]
# push_uri与base_uri对应关系(排名分先后)(就是这么奇葩..) services = [ (‘wx2.qq.com‘, ‘webpush2.weixin.qq.com‘), (‘qq.com‘, ‘webpush.weixin.qq.com‘), (‘web1.wechat.com‘, ‘webpush1.wechat.com‘), (‘web2.wechat.com‘, ‘webpush2.wechat.com‘), (‘wechat.com‘, ‘webpush.wechat.com‘), (‘web1.wechatapp.com‘, ‘webpush1.wechatapp.com‘), ] push_uri = base_uri for (searchUrl, pushUrl) in services: if base_uri.find(searchUrl) >= 0: push_uri = ‘https://%s/cgi-bin/mmwebwx-bin‘ % pushUrl break
# closeQRImage if sys.platform.find(‘darwin‘) >= 0: # for OSX with Preview os.system("osascript -e ‘quit app \"Preview\"‘") elif code == ‘408‘: # 超时 pass # elif code == ‘400‘ or code == ‘500‘:
return code
def login(): global skey, wxsid, wxuin, pass_ticket, BaseRequest
r = myRequests.get(url=redirect_uri) r.encoding = ‘utf-8‘ data = r.text
# print(data)
doc = xml.dom.minidom.parseString(data) root = doc.documentElement
for node in root.childNodes: if node.nodeName == ‘skey‘: skey = node.childNodes[0].data elif node.nodeName == ‘wxsid‘: wxsid = node.childNodes[0].data elif node.nodeName == ‘wxuin‘: wxuin = node.childNodes[0].data elif node.nodeName == ‘pass_ticket‘: pass_ticket = node.childNodes[0].data
# print(‘skey: %s, wxsid: %s, wxuin: %s, pass_ticket: %s‘ % (skey, wxsid, # wxuin, pass_ticket))
if not all((skey, wxsid, wxuin, pass_ticket)): return False
BaseRequest = { ‘Uin‘: int(wxuin), ‘Sid‘: wxsid, ‘Skey‘: skey, ‘DeviceID‘: deviceId, }
return True
def webwxinit(): url = (base_uri + ‘/webwxinit?pass_ticket=%s&skey=%s&r=%s‘ % ( pass_ticket, skey, int(time.time()))) params = {‘BaseRequest‘: BaseRequest} headers = {‘content-type‘: ‘application/json; charset=UTF-8‘}
r = myRequests.post(url=url, data=json.dumps(params), headers=headers) r.encoding = ‘utf-8‘ data = r.json()
if DEBUG: f = open(os.path.join(os.getcwd(), ‘webwxinit.json‘), ‘wb‘) f.write(r.content) f.close()
# print(data)
global ContactList, My, SyncKey dic = data ContactList = dic[‘ContactList‘] My = dic[‘User‘] SyncKey = dic[‘SyncKey‘]
state = responseState(‘webwxinit‘, dic[‘BaseResponse‘]) return state
def webwxgetcontact(): url = (base_uri + ‘/webwxgetcontact?pass_ticket=%s&skey=%s&r=%s‘ % ( pass_ticket, skey, int(time.time()))) headers = {‘content-type‘: ‘application/json; charset=UTF-8‘}
r = myRequests.post(url=url, headers=headers) r.encoding = ‘utf-8‘ data = r.json()
if DEBUG: f = open(os.path.join(os.getcwd(), ‘webwxgetcontact.json‘), ‘wb‘) f.write(r.content) f.close()
dic = data MemberList = dic[‘MemberList‘]
# 倒序遍历,不然删除的时候出问题.. SpecialUsers = ["newsapp", "fmessage", "filehelper", "weibo", "qqmail", "tmessage", "qmessage", "qqsync", "floatbottle", "lbsapp", "shakeapp", "medianote", "qqfriend", "readerapp", "blogapp", "facebookapp", "masssendapp", "meishiapp", "feedsapp", "voip", "blogappweixin", "weixin", "brandsessionholder", "weixinreminder", "wxid_novlwrv3lqwv11", "gh_22b87fa7cb3c", "officialaccounts", "notification_messages", "wxitil", "userexperience_alarm"] for i in range(len(MemberList) - 1, -1, -1): Member = MemberList[i] if Member[‘VerifyFlag‘] & 8 != 0: # 公众号/服务号 MemberList.remove(Member) elif Member[‘UserName‘] in SpecialUsers: # 特殊账号 MemberList.remove(Member) elif Member[‘UserName‘].find(‘@@‘) != -1: # 群聊 MemberList.remove(Member) elif Member[‘UserName‘] == My[‘UserName‘]: # 自己 MemberList.remove(Member)
return MemberList
def syncKey(): SyncKeyItems = [‘%s_%s‘ % (item[‘Key‘], item[‘Val‘]) for item in SyncKey[‘List‘]] SyncKeyStr = ‘|‘.join(SyncKeyItems) return SyncKeyStr
def syncCheck(): url = push_uri + ‘/synccheck?‘ params = { ‘skey‘: BaseRequest[‘Skey‘], ‘sid‘: BaseRequest[‘Sid‘], ‘uin‘: BaseRequest[‘Uin‘], ‘deviceId‘: BaseRequest[‘DeviceID‘], ‘synckey‘: syncKey(), ‘r‘: int(time.time()), }
r = myRequests.get(url=url, params=params) r.encoding = ‘utf-8‘ data = r.text
# print(data)
# window.synccheck={retcode:"0",selector:"2"} regx = r‘window.synccheck={retcode:"(\d+)",selector:"(\d+)"}‘ pm = re.search(regx, data)
retcode = pm.group(1) selector = pm.group(2)
return selector
def webwxsync(): global SyncKey
url = base_uri + ‘/webwxsync?lang=zh_CN&skey=%s&sid=%s&pass_ticket=%s‘ % ( BaseRequest[‘Skey‘], BaseRequest[‘Sid‘], urllib.quote_plus(pass_ticket)) params = { ‘BaseRequest‘: BaseRequest, ‘SyncKey‘: SyncKey, ‘rr‘: ~int(time.time()), } headers = {‘content-type‘: ‘application/json; charset=UTF-8‘}
r = myRequests.post(url=url, data=json.dumps(params)) r.encoding = ‘utf-8‘ data = r.json()
# print(data)
dic = data SyncKey = dic[‘SyncKey‘]
state = responseState(‘webwxsync‘, dic[‘BaseResponse‘]) return state
def heartBeatLoop(): while True: selector = syncCheck() if selector != ‘0‘: webwxsync() time.sleep(1)
def main(): global myRequests
if hasattr(ssl, ‘_create_unverified_context‘): ssl._create_default_https_context = ssl._create_unverified_context
headers = { ‘User-agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.125 Safari/537.36‘} myRequests = requests.Session() myRequests.headers.update(headers)
if not getUUID(): print(‘获取uuid失败‘) return
print(‘正在获取二维码图片...‘) showQRImage()
while waitForLogin() != ‘200‘: pass
os.remove(QRImagePath)
if not login(): print(‘登录失败‘) return
if not webwxinit(): print(‘初始化失败‘) return
MemberList = webwxgetcontact()
threading.Thread(target=heartBeatLoop)
MemberCount = len(MemberList) print(‘通讯录共%s位好友‘ % MemberCount)
d = {} imageIndex = 0 for Member in MemberList: imageIndex = imageIndex + 1 # name = ‘C:\\Users\\Public\\Pictures\\‘ + str(imageIndex) + ‘.jpg‘ # imageUrl = ‘http://wx2.qq.com‘ + Member[‘HeadImgUrl‘] # r = myRequests.get(url=imageUrl, headers=headers) # imageContent = (r.content) # fileImage = open(name, ‘wb‘) # fileImage.write(imageContent) # fileImage.close() # print(‘正在下载第：‘ + str(imageIndex) + ‘位好友头像‘) d[Member[‘UserName‘]] = (Member[‘NickName‘], Member[‘RemarkName‘]) city = Member[‘City‘] city = ‘nocity‘ if city == ‘‘ else city name = Member[‘NickName‘] name = ‘noname‘ if name == ‘‘ else name sign = Member[‘Signature‘] sign = ‘nosign‘ if sign == ‘‘ else sign remark = Member[‘RemarkName‘] remark = ‘noremark‘ if remark == ‘‘ else remark alias = Member[‘Alias‘] alias = ‘noalias‘ if alias == ‘‘ else alias nick = Member[‘NickName‘] nick = ‘nonick‘ if nick == ‘‘ else nick print(name, ‘|||‘, city, ‘|||‘, Member[‘Sex‘], ‘|||‘, Member[‘StarFriend‘], ‘|||‘, sign, ‘|||‘, remark, ‘|||‘, alias, ‘|||‘, nick)
if __name__ == ‘__main__‘: main() print(‘回车键退出...‘) input()
程序运行过程中会跳出二维码，需要我们扫描登录
作者原文基于mac，所以我自己修改成了这个样子（红色加粗和蓝色底纹部分）
subprocess.call([‘open‘, QRImagePath]) 是给linux或mac下用来打开文件的
而windows下要用os.startfile(QRImagePath)（不要问我怎么知道的，我运行报错后猜出它的作用然后百度的）
（感谢好友的一路陪伴和困厄之时的支持）
微信头像被保存在对应的文件路径C:\\Users\\Public\\Pictures\\中
在CSV中：
经过分析（借助了EasyChart的配色）：
神奇，居然还是女生多？难道是最近加我的微信或者骗子比较多嘛？
文件
参考：
Python对微信好友进行简单统计分析
https://zhuanlan.zhihu.com/p/21967333?fc=1&group_id=747709381369417728
当Python遇上微信，可以这么玩
https://zhuanlan.zhihu.com/p/26514576?group_id=839173221667446784
echarts
http://echarts.baidu.com/index.html
******************************?******************************
抓取淘宝宝贝信息
代码如下：
import refrom selenium import webdriverfrom selenium.common.exceptions import TimeoutExceptionfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom pyquery import PyQuery as pqfrom taobao.config import *import pymongo
client = pymongo.MongoClient(MONGO_URL)db = client[MONGO_DB]
browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)wait = WebDriverWait(browser, 10)#设置窗口大小，以免默认的相对较小的窗口影响操作browser.set_window_size(1400, 900)
def search(): print(‘正在搜索‘) try: browser.get(‘https://www.taobao.com‘) # http://selenium-python.readthedocs.io/waits.html#explicit-waits # 输入框 input = wait.until( EC.presence_of_element_located((By.CSS_SELECTOR, ‘#q‘)) ) #搜索提交按钮 submit = wait.until( EC.element_to_be_clickable((By.CSS_SELECTOR, ‘#J_TSearchForm > div.search-button > button‘)))
input.send_keys(KEYWORD) submit.click()
#等待搜索内容加载，表示为共x页 total = wait.until( EC.presence_of_element_located((By.CSS_SELECTOR, ‘#mainsrp-pager > div > div > div > div.total‘))) #total中就是总共有多少页 get_products() return total.text except TimeoutException: # wait在网速过慢的时候会出现超时错误，所以我们递归调用重新请求 return search()
def next_page(page_number): #进入下一页有多种方式，比如点击xx页，比如点击下一页按钮 #比如在输入框中设置页码，点击确定 #我们采用最后一种，因为第一章容易错乱 #而最后一种相比于第二种方便我们在出错的时候递归 print(‘正在翻页‘, page_number) try: #输入页码框 input = wait.until( EC.presence_of_element_located((By.CSS_SELECTOR, ‘#mainsrp-pager > div > div > div > div.form > input‘)) ) #提交按钮 submit = wait.until(EC.element_to_be_clickable( (By.CSS_SELECTOR, ‘#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit‘))) #清楚原先的页码 input.clear() input.send_keys(page_number) submit.click() #判断翻页是否成功（判断条件是高亮的当前代码） wait.until(EC.text_to_be_present_in_element( (By.CSS_SELECTOR, ‘#mainsrp-pager > div > div > div > ul > li.item.active > span‘), str(page_number))) get_products() except TimeoutException: #出错则递归，重新执行 next_page(page_number)
#解析def get_products(): #判断所有的宝贝信息是否传递成功 wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, ‘#mainsrp-itemlist .items .item‘))) html = browser.page_source doc = pq(html) items = doc(‘#mainsrp-itemlist .items .item‘).items() for item in items: product = { ‘image‘: item.find(‘.pic .img‘).attr(‘src‘), ‘price‘: item.find(‘.price‘).text(), ‘deal‘: item.find(‘.deal-cnt‘).text()[:-3], ‘title‘: item.find(‘.title‘).text(), ‘shop‘: item.find(‘.shop‘).text(), ‘location‘: item.find(‘.location‘).text() } print(product) save_to_mongo(product)
#保存def save_to_mongo(result): try: if db[MONGO_TABLE].insert(result): print(‘存储到MONGODB成功‘, result) except Exception: print(‘存储到MONGODB失败‘, result)
def main(): try: total = search() #提取总页数 total = int(re.compile(‘(\d+)‘).search(total).group(1)) for i in range(2, total + 1): #从第二页才开始需要点击下一页 next_page(i) except Exception: print(‘出错啦‘) finally: browser.close()
if __name__ == ‘__main__‘: main()
注意，是在Python3下
config文件（上面标红的config的引入路径要根据实际情况修改）
MONGO_URL = ‘localhost‘MONGO_DB = ‘taobao‘MONGO_TABLE = ‘product‘ # http://phantomjs.org/api/command-line.html#第一个参数是不加载图片，使程序运行更快#第二个的开启缓存SERVICE_ARGS = [‘--load-images=false‘, ‘--disk-cache=true‘] KEYWORD = ‘汉服‘
******************************?******************************
抓取今日头条
代码如下：
import jsonimport osfrom urllib.parse import urlencodeimport pymongoimport requestsfrom bs4 import BeautifulSoupfrom requests.exceptions import ConnectionErrorimport refrom multiprocessing import Poolfrom hashlib import md5from json.decoder import JSONDecodeErrorfrom spider_basic.config import *
#client = pymongo.MongoClient(MONGO_URL, connect=False)db = client[MONGO_DB]
#获取主页，offse是ajax动态加载的偏移量，keyword是搜索的关键字def get_page_index(offset, keyword): data = { ‘autoload‘: ‘true‘, ‘count‘: 20, ‘cur_tab‘: 3, ‘format‘: ‘json‘, ‘keyword‘: keyword, ‘offset‘: offset, } params = urlencode(data) base = ‘http://www.toutiao.com/search_content/‘ url = base + ‘?‘ + params try: response = requests.get(url) if response.status_code == 200: return response.text return None except ConnectionError: print(‘Error occurred‘) return None
#下载def download_image(url): print(‘Downloading‘, url) try: response = requests.get(url) if response.status_code == 200: save_image(response.content) return None except ConnectionError: return None
#保存def save_image(content): # 文件名 # 路径 名称 后缀 # 名称md5 这是为了当我们运行一次程序出错时，第二次不再保存重复图片 file_path = ‘{0}/{1}/{2}.{3}‘.format(os.getcwd(),‘pic‘,md5(content).hexdigest(), ‘jpg‘) print(file_path) # 如果文件不存在则保存 # content是二进制形式的网页内容 if not os.path.exists(file_path): with open(file_path, ‘wb‘) as f: f.write(content) f.close()
#解析搜索后返回的网页（就是图集XHR中的那些）def parse_page_index(text): try: #转化为JSON data = json.loads(text) #如果JSON数据中含有data这个键 if data and ‘data‘ in data.keys(): for item in data.get(‘data‘): yield item.get(‘article_url‘) except JSONDecodeError: pass
#获取详情页def get_page_detail(url): try: response = requests.get(url) if response.status_code == 200: return response.text return None except ConnectionError: print(‘Error occurred‘) return None
#解析详情页def parse_page_detail(html, url): soup = BeautifulSoup(html, ‘lxml‘) #获取标题 result = soup.select(‘title‘) title = result[0].get_text() if result else ‘‘ #获取图片地址（定义正则规则，并search） images_pattern = re.compile(‘var gallery = (.*?);‘, re.S) result = re.search(images_pattern, html) #如果非空 if result: #转化为JSON格式 data = json.loads(result.group(1)) #如果sub_images这个键的值对应了各种url if data and ‘sub_images‘ in data.keys(): sub_images = data.get(‘sub_images‘) images = [item.get(‘url‘) for item in sub_images] #下载图片 for image in images: download_image(image) return { ‘title‘: title, ‘url‘: url, ‘images‘: images }
#存储到数据库def save_to_mongo(result): if db[MONGO_TABLE].insert(result): print(‘Successfully Saved to Mongo‘, result) return True return False
def main(offset): text = get_page_index(offset, KEYWORD) #生成器返回图集中每一个图集的URL的遍历器 urls = parse_page_index(text) #遍历每一个图集，获取详情页信息 for url in urls: #获取详情页 html = get_page_detail(url) #解析详情页 result = parse_page_detail(html, url) #保存到MongoDB if result: save_to_mongo(result)
# if __name__ == ‘__main__‘:# main(60)
# 注意，如果不在if __name__ == ‘__main__‘:中运行的话，会爆出一堆多线程的错误if __name__ == ‘__main__‘: pool = Pool() groups = ([x * 20 for x in range(GROUP_START, GROUP_END + 1)]) pool.map(main, groups) pool.close() pool.join()
config文件
MONGO_URL = ‘localhost‘MONGO_DB = ‘toutiao‘MONGO_TABLE = ‘toutiao‘ GROUP_START = 1GROUP_END = 20KEYWORD=‘萌宠‘
附件列表
时间： 2024-10-06 06:37:48