[已解决]正则表达式疑问

TCY · 发表于 2018-11-29 12:00:48

马上注册，结交更多好友，享用更多功能^_^

您需要登录才可以下载或查看，没有账号？立即注册

x

按小甲鱼抄的代码：

import requests
import re
import json
def open_url(keyword, page = 1):
keyword = "零基础入门学习Python"
url = "https://s.taobao.com/search"
headers = {"user-agent":"Mozilla/5.0 (Windows NT 10; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.90 Safari/537.36"}
payload = {"q":keyword, "s":str((page - 1) * 44), "sort":"sale-desc"}
cookie = "miid=690527322662134086; thw=cn; UM_distinctid=1659eebc48e99-00e0b2b034ef5a-62381459-1fa400-1659eebc4902bf; l=AoGB-NWrd3CEx0CI6qw241RwEcebJvWg; cna=zB4ZE5L/q20CAbfr/zVbsY5J; hng=CN%7Czh-CN%7CCNY%7C156; t=85f066376cd3704954202a09357ed24e; uc3=vt3=F8dByR6qJyiNQbhgu%2Fs%3D&id2=UUjZelQJ%2FHgrhw%3D%3D&nk2=oggiitQFuUg%3D&lg2=V32FPkk%2Fw0dUvg%3D%3D; tracknick=%5Cu9F99%5Cu7FBD%5Cu5728%5Cu7EBF; lgc=%5Cu9F99%5Cu7FBD%5Cu5728%5Cu7EBF; _cc_=W5iHLLyFfA%3D%3D; tg=0; mt=ci=74_1&np=; enc=C6HRarQIhzItaDsqCtcXB8U3FXkxG8v2xp0JJQADDfaffT8yvfanzKAEkCa5p6rEa2eeyjwNiqldnXNGba0LaA%3D%3D; _m_h5_tk=59bfb65378d094565372a91915643c0d_1543200189078; _m_h5_tk_enc=c52360670f3df78c7eb74d43c00809e6; _uab_collina=154339793326366672140839; cookie2=1488a1089e99113bcb94bdd451e6b343; _tb_token_=ee498a173753e; v=0; JSESSIONID=323A8F673C27B702D720B38855E5DBC6; isg=BBsbL3SFxF17jjiN_3ITCMg7vX9FWC6WAc-5Bw1Y9Zox7DvOlcBeQE9uggxHTIfq"
cookies = {}
for each in cookie.split("; "):
name, value = each.strip().split("=", 1)
cookies[name] = value
res = requests.get(url, params = payload, headers = headers, cookies = cookies)
return res
def get_items(res):
g_page_config = re.search(r"g_page_config = (.*?);\n", res.text).group(1)
page_config_json = json.loads(g_page_config)
page_items = page_config_json["mods"]["itemlist"]["data"]["auctions"]
results = []
for each_item in page_items:
temp = dict.fromkeys(("nid", "title", "detail_url", "view_price", "view_sales", "nick"))
temp["nid"] = each_item["nid"]
temp["title"] = each_item["title"]
temp["detail_url"] = each_item["detail_url"]
temp["view_price"] = each_item["view_price"]
temp["nick"] = each_item["nick"]
results.append(temp)
return results
def count_sales(items):
count = 0
for each in items:
if "小甲鱼" in each["title"]:
count += int(re.search(r"\d+", each["view_sales"]).group())
return count
def main():
global res
keyword = input("请输入要查询的商品：")
length = 3
total = 0
for each in range(length):
res = open_url(keyword, each + 1)
items = get_items(res)
total += count_sales(items)
print("总销量是：%s", total)
if __name__ == "__main__":
main()

复制代码

结果：

>>>
请输入要查询的商品：
Traceback (most recent call last):
File "C:\Users\admin\Desktop\统计销量.py", line 54, in <module>
main()
File "C:\Users\admin\Desktop\统计销量.py", line 50, in main
total += count_sales(items)
File "C:\Users\admin\Desktop\统计销量.py", line 38, in count_sales
count += int(re.search(r"\d+", each["view_sales"]).group())
File "D:\Python\lib\re.py", line 183, in search
return _compile(pattern, flags).search(string)
TypeError: expected string or bytes-like object
>>>

复制代码

怎么回事？？？？
@塔利班

最佳答案

月排行榜 / 总排行榜

塔利班

2018-11-30 08:41:06

for each_item in page_items:
      temp = dict.fromkeys(("nid", "title", "detail_url", "view_price", "view_sales", "nick"))
      temp["nid"] = each_item["nid"]
      temp["title"] = each_item["title"]
      temp["detail_url"] = each_item["detail_url"]
      temp["view_price"] = each_item["view_price"]
      temp["nick"] = each_item["nick"]
getitems哪里就没有给view_sales添加value

跳转到最佳答案楼层

TCY · 发表于 2018-11-29 12:02:31

我还发现each["view_sales"]是None，神马情况？

塔利班 · 发表于 2018-11-29 12:38:15

TCY 发表于 2018-11-29 12:02
我还发现each["view_sales"]是None，神马情况？

那就首先是None,导致你不能用正则，更不能用int

TCY · 发表于 2018-11-29 19:23:10

代码改了：

import requests
import re
import json
def open_url(keyword, page = 1):
keyword = "零基础入门学习Python"
url = "https://s.taobao.com/search"
headers = {"user-agent":"Mozilla/5.0 (Windows NT 10; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.90 Safari/537.36"}
payload = {"q":keyword, "s":str((page - 1) * 44), "sort":"sale-desc"}
cookie = "miid=690527322662134086; thw=cn; UM_distinctid=1659eebc48e99-00e0b2b034ef5a-62381459-1fa400-1659eebc4902bf; l=AoGB-NWrd3CEx0CI6qw241RwEcebJvWg; cna=zB4ZE5L/q20CAbfr/zVbsY5J; hng=CN%7Czh-CN%7CCNY%7C156; t=85f066376cd3704954202a09357ed24e; uc3=vt3=F8dByR6qJyiNQbhgu%2Fs%3D&id2=UUjZelQJ%2FHgrhw%3D%3D&nk2=oggiitQFuUg%3D&lg2=V32FPkk%2Fw0dUvg%3D%3D; tracknick=%5Cu9F99%5Cu7FBD%5Cu5728%5Cu7EBF; lgc=%5Cu9F99%5Cu7FBD%5Cu5728%5Cu7EBF; _cc_=W5iHLLyFfA%3D%3D; tg=0; mt=ci=74_1&np=; enc=C6HRarQIhzItaDsqCtcXB8U3FXkxG8v2xp0JJQADDfaffT8yvfanzKAEkCa5p6rEa2eeyjwNiqldnXNGba0LaA%3D%3D; _m_h5_tk=59bfb65378d094565372a91915643c0d_1543200189078; _m_h5_tk_enc=c52360670f3df78c7eb74d43c00809e6; _uab_collina=154339793326366672140839; cookie2=1488a1089e99113bcb94bdd451e6b343; _tb_token_=ee498a173753e; v=0; JSESSIONID=323A8F673C27B702D720B38855E5DBC6; isg=BBsbL3SFxF17jjiN_3ITCMg7vX9FWC6WAc-5Bw1Y9Zox7DvOlcBeQE9uggxHTIfq"
cookies = {}
for each in cookie.split("; "):
name, value = each.strip().split("=", 1)
cookies[name] = value
res = requests.get(url, params = payload, headers = headers, cookies = cookies)
return res
def get_items(res):
g_page_config = re.search(r"g_page_config = (.*?);\n", res.text).group(1)
page_config_json = json.loads(g_page_config)
page_items = page_config_json["mods"]["itemlist"]["data"]["auctions"]
results = []
for each_item in page_items:
temp = dict.fromkeys(("nid", "title", "detail_url", "view_price", "view_sales", "nick"))
temp["nid"] = each_item["nid"]
temp["title"] = each_item["title"]
temp["detail_url"] = each_item["detail_url"]
temp["view_price"] = each_item["view_price"]
temp["nick"] = each_item["nick"]
results.append(temp)
return results
def count_sales(items):
count = 0
for each in items:
if "小甲鱼" in each["title"]:
print(each["view_sales"]) #测试
if type(each["view_sales"]) == int:
count += each["view_sales"]
elif type(each["view_sales"]) == str:
count += int(re.search(r"\d+", each["view_sales"]).group())
return count
def main():
keyword = input("请输入要查询的商品：")
length = 3
total = 0
for each in range(length):
res = open_url(keyword, each + 1)
items = get_items(res)
total += count_sales(items)
print("总销量是：%d" % total)
if __name__ == "__main__":
main()

复制代码

结果：

>>>
================== RESTART: C:\Users\admin\Desktop\统计销量.py ==================
请输入要查询的商品：
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
总销量是：0
>>>

复制代码

什么情况？

塔利班 · 发表于 2018-11-29 19:35:21

我运行几次就被淘宝和谐了，你的None,肯定是字典没有这个键啊，你可以试着打印each，看到底有啥，

TCY · 发表于 2018-11-30 07:15:12

each有：

{'nid': '555843337517', 'title': '零基础入门学习Python 小甲鱼计算机/网络 pyhton3.0从入门到精通python语言程序设计基础核心教程 python编程从入门到实践书籍', 'detail_url': '//detail.tmall.com/item.htm?id=555843337517&ns=1&abbucket=19', 'view_price': '29.50', 'view_sales': None, 'nick': '墨涵图书专营店'}
{'nid': '571066530112', 'title': '正版现货 零基础学Python python编程从入门到实践书籍零基础入门学习pyhton从入门到精通python语言程序设计基础教程小甲鱼书籍', 'detail_url': '//detail.tmall.com/item.htm?id=571066530112&ns=1&abbucket=19', 'view_price': '38.80', 'view_sales': None, 'nick': '拓创图书专营店'}
{'nid': '579472364014', 'title': 'Python从入门到精通核心编程入门书籍零基础学习网络爬虫 python编程从入门到实践 python基础教程语言程序设计算机教材书小甲鱼', 'detail_url': '//detail.tmall.com/item.htm?id=579472364014&ns=1&abbucket=19', 'view_price': '44.90', 'view_sales': None, 'nick': '墨马图书专营店'}
{'nid': '541062793793', 'title': '【官方正版】 零基础入门学习Python 李佳宇清华大学出版社 零基础入门学习Python 小甲鱼计算机/网络 pyhton3.0从入门到精通', 'detail_url': '//detail.tmall.com/item.htm?id=541062793793&ns=1&abbucket=19', 'view_price': '39.60', 'view_sales': None, 'nick': '清华大学出版社官方旗舰店'}
{'nid': '541449698302', 'title': 'python基础教程 零基础入门学习Python 3 鱼C工作室小甲鱼编著程序设计核心编程从入门到实践学习手册', 'detail_url': '//detail.tmall.com/item.htm?id=541449698302&ns=1&abbucket=19', 'view_price': '34.60', 'view_sales': None, 'nick': '赣江图书专营'}
{'nid': '579655409664', 'title': 'Python从入门到精通核心编程入门书籍零基础学习网络爬虫 python编程从入门到实践 python基础教程语言程序设计算机教材书小甲鱼', 'detail_url': '//detail.tmall.com/item.htm?id=579655409664&ns=1&abbucket=19', 'view_price': '39.90', 'view_sales': None, 'nick': '墨涵图书专营店'}
{'nid': '579670869230', 'title': '现货 零基础学Python python编程从入门到实践书籍零基础入门学习pyhton从入门到精通python语言程序设计基础教程小甲鱼书籍', 'detail_url': '//detail.tmall.com/item.htm?id=579670869230&ns=1&abbucket=19', 'view_price': '38.80', 'view_sales': None, 'nick': '悦悦图书专营店'}
{'nid': '579932211992', 'title': '零基础学Python 全彩版自学python编程从入门到实践书籍零基础入门学习pyhton从入门到精通python语言程序设计基础教程小甲鱼书籍', 'detail_url': '//detail.tmall.com/item.htm?id=579932211992&ns=1&abbucket=19', 'view_price': '38.80', 'view_sales': None, 'nick': '志达图书专营店'}
{'nid': '561770269350', 'title': '正版 零基础入门学习Python 小甲鱼 pyhton3.0从入门到精通python语言程序设计基础核心教程 python编程从入门到实践书籍', 'detail_url': '//detail.tmall.com/item.htm?id=561770269350&ns=1&abbucket=19', 'view_price': '34.70', 'view_sales': None, 'nick': '文舟图书专营店'}
{'nid': '570056748205', 'title': '正版现货 零基础学Python python编程从入门到实践书籍零基础入门学习pyhton从入门到精通python语言程序设计基础教程小甲鱼书籍', 'detail_url': '//detail.tmall.com/item.htm?id=570056748205&ns=1&abbucket=19', 'view_price': '39.80', 'view_sales': None, 'nick': '墨涵图书专营店'}
{'nid': '578839556879', 'title': '正版现货 零基础入门学习Python 小甲鱼计算机/网络编程语言 python从入门到精通基础教程清华大学出版社从入门到实践书', 'detail_url': '//detail.tmall.com/item.htm?id=578839556879&ns=1&abbucket=19', 'view_price': '41.10', 'view_sales': None, 'nick': '智友图书专营店'}
{'nid': '556720642214', 'title': '正版【赠97集视频课】 零基础入门学习Python 小甲鱼程序设计计算机核心编程从入门到实践学习手册 Python网络编程知识基础图书籍', 'detail_url': '//detail.tmall.com/item.htm?id=556720642214&ns=1&abbucket=19', 'view_price': '37.90', 'view_sales': None, 'nick': '凤凰新华书店旗舰店'}
{'nid': '541808534505', 'title': '零基础入门学习Python 小甲鱼计算机/网络程序设计核心编程 python基础教程 pyhton从入门到精通python3.0编程从入门到实践书籍', 'detail_url': '//detail.tmall.com/item.htm?id=541808534505&ns=1&abbucket=19', 'view_price': '34.70', 'view_sales': None, 'nick': '山东书虫图书专营店'}
{'nid': '561936987691', 'title': '零基础入门学习python小甲鱼编程从零开始到实践python3网络爬虫开发实战免费扫码视频教程计算机项目实践python语言程序设计书籍', 'detail_url': '//detail.tmall.com/item.htm?id=561936987691&ns=1&abbucket=19', 'view_price': '39.90', 'view_sales': None, 'nick': '华夏学林图书专营店'}
{'nid': '576086945521', 'title': '中学生可以这样学Python+零基础入门学习Python共2本小甲鱼 Python3基础入门书籍初中高中生学Python编程书游戏开发制作图书籍', 'detail_url': '//detail.tmall.com/item.htm?id=576086945521&ns=1&abbucket=19', 'view_price': '63.80', 'view_sales': None, 'nick': '兰兴达图书专营店'}
{'nid': '570184909870', 'title': '正版现货 零基础学Python python编程从入门到实践书籍零基础入门学习pyhton从入门到精通python语言程序设计基础教程小甲鱼书籍', 'detail_url': '//detail.tmall.com/item.htm?id=570184909870&ns=1&abbucket=19', 'view_price': '39.80', 'view_sales': None, 'nick': '墨马图书专营店'}
{'nid': '542167468512', 'title': '零基础入门学习Python Python3入门教程 Python开发教程 Python3在爬虫 Tkinter 游戏开发应用小甲鱼著 Python编程序设计', 'detail_url': '//detail.tmall.com/item.htm?id=542167468512&ns=1&abbucket=19', 'view_price': '36.60', 'view_sales': None, 'nick': '拓创图书专营店'}
{'nid': '543872715690', 'title': '零基础入门学习python编程从入门到实践小甲鱼 python学习手册 python视频教程清华社语言程序设计 python爬虫开发实战教程', 'detail_url': '//detail.tmall.com/item.htm?id=543872715690&ns=1&abbucket=19', 'view_price': '29.00', 'view_sales': None, 'nick': '百华图书专营店'}
{'nid': '575941757954', 'title': 'python编程从入门到实践 零基础入门学习Python 3.0小甲鱼程序设计核心编程学习手册 python基础教程学习手册书籍', 'detail_url': '//detail.tmall.com/item.htm?id=575941757954&ns=1&abbucket=19', 'view_price': '34.60', 'view_sales': None, 'nick': '翔坤图书专营店'}
{'nid': '565369647169', 'title': '二手满58元包邮 零基础入门学习Python 小甲鱼清华大学出版社', 'detail_url': '//item.taobao.com/item.htm?id=565369647169&ns=1&abbucket=19#detail', 'view_price': '22.00', 'view_sales': None, 'nick': '科大考研1'}
{'nid': '555764232213', 'title': '零基础入门学习Python 小甲鱼计算机/网络程序设计 零基础学编程 python基础学习手册 python从入门到精通Python程序设计教程书籍', 'detail_url': '//detail.tmall.com/item.htm?id=555764232213&ns=1&abbucket=19', 'view_price': '34.65', 'view_sales': None, 'nick': '墨马图书专营店'}
{'nid': '555938767185', 'title': '零基础入门学习Python 小甲鱼计算机/网络程序设计 零基础学编程 python基础学习手册 python从入门到精通Python程序设计教程书籍', 'detail_url': '//detail.tmall.com/item.htm?id=555938767185&ns=1&abbucket=19', 'view_price': '29.70', 'view_sales': None, 'nick': '馨园青图书专营店'}
{'nid': '563648067060', 'title': '中学生可以这样学Python+零基础入门学习Python 小甲鱼 Python3基础入门教程书籍初中高中生学Python编程教程书籍游戏开发制作书', 'detail_url': '//detail.tmall.com/item.htm?id=563648067060&ns=1&abbucket=19', 'view_price': '65.80', 'view_sales': None, 'nick': '云聚算图书专营店'}
{'nid': '580120091081', 'title': '【送96集视频教程Python编程教程书籍】零基础入门学习Python小甲鱼李佳宇 Python3入门教程书籍Python开发 Python基础教程书籍web', 'detail_url': '//detail.tmall.com/item.htm?id=580120091081&ns=1&abbucket=19', 'view_price': '41.60', 'view_sales': None, 'nick': '智源图书专营店'}
{'nid': '556705668287', 'title': '零基础入门学习Python 小甲鱼计算机/网络 pyhton3.0从入门到精通python语言程序设计基础核心教程 python编程从入门到实践书籍', 'detail_url': '//detail.tmall.com/item.htm?id=556705668287&ns=1&abbucket=19', 'view_price': '39.70', 'view_sales': None, 'nick': '悦悦图书专营店'}
{'nid': '541799097670', 'title': '包邮 零基础入门学习Python Python3入门教程 Python开发教程 Python3在爬虫 Tkinter 游戏开发应用小甲鱼著 Python编程序设计', 'detail_url': '//detail.tmall.com/item.htm?id=541799097670&ns=1&abbucket=19', 'view_price': '34.60', 'view_sales': None, 'nick': '布克图书专营店'}
{'nid': '552428334517', 'title': 'python基础教程从入门到实践书籍小甲鱼清华大学出版社 3零基础利用python进行数据分析简明爬虫核心编程机器学习 配视频课件', 'detail_url': '//detail.tmall.com/item.htm?id=552428334517&ns=1&abbucket=19', 'view_price': '39.83', 'view_sales': None, 'nick': '腾文图书专营店'}
{'nid': '564905239930', 'title': '正版现货包邮 零基础入门学习Python 小甲鱼计算机网络程序设计核心编程从入门到精通python3.0编程工具书新华书店畅销书籍jn', 'detail_url': '//detail.tmall.com/item.htm?id=564905239930&ns=1&abbucket=19', 'view_price': '34.50', 'view_sales': None, 'nick': '漂流图书专营店'}
{'nid': '543332581749', 'title': '零基础入门学习Python 小甲鱼著 Python3基础语法 Python3入门教程 Python3游戏开发编程 python核心编程学习手册旷氏文豪', 'detail_url': '//detail.tmall.com/item.htm?id=543332581749&ns=1&abbucket=19', 'view_price': '34.65', 'view_sales': None, 'nick': '旷氏文豪图书专营店'}
{'nid': '561905371350', 'title': '正版包邮零基础入门学习Python（水木书荟）python基础学习手册小甲鱼计算机/网络程序设计 零基础学编程 pyhton从入门到精通', 'detail_url': '//detail.tmall.com/item.htm?id=561905371350&ns=1&abbucket=19', 'view_price': '34.65', 'view_sales': None, 'nick': '启诚图书专营店'}
{'nid': '578097127158', 'title': '满3件包邮零基础入门学习Python 小甲鱼经典丛书', 'detail_url': '//item.taobao.com/item.htm?id=578097127158&ns=1&abbucket=19#detail', 'view_price': '18.00', 'view_sales': None, 'nick': '大众图书城688'}
{'nid': '559012201470', 'title': '正版现货 零基础入门学习Python 3.0小甲鱼程序设计核心编程学习手册 python编程从入门到实践python基础教程学习手册书籍', 'detail_url': '//detail.tmall.com/item.htm?id=559012201470&ns=1&abbucket=19', 'view_price': '34.60', 'view_sales': None, 'nick': '华心图书专营店'}

复制代码

塔利班 · 发表于 2018-11-30 08:41:06

for each_item in page_items:
      temp = dict.fromkeys(("nid", "title", "detail_url", "view_price", "view_sales", "nick"))
      temp["nid"] = each_item["nid"]
      temp["title"] = each_item["title"]
      temp["detail_url"] = each_item["detail_url"]
      temp["view_price"] = each_item["view_price"]
      temp["nick"] = each_item["nick"]
getitems哪里就没有给view_sales添加value

账号		自动登录	找回密码
密码			立即注册

[已解决]正则表达式疑问

马上注册，结交更多好友，享用更多功能^_^

浏览过的版块