#https://www.lagou.com/jobs/positionAjax.json?city=%E4%B8%8A%E6%B5%B7&needAddtionalResult=false
import requests
#实际要爬取的url
url = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'
payload = {
'first': 'true',
'pn': '1',
'kd': 'python',
}
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
'Referer': 'https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=',
'Accept': 'application/json, text/javascript, */*; q=0.01'
}
#原始的url
urls ='https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput='
#建立session
s = requests.Session()
# 获取搜索页的cookies
s.get(urls, headers=header, timeout=3)
# 为此次获取的cookies
cookie = s.cookies
# 获取此次文本
response = s.post(url, data=payload, headers=header, cookies=cookie, timeout=5).text
print(response)
爬取红楼梦小说
2 爬红楼梦小说
#http://www.shicimingju.com/book/hongloumeng.html
import requests
from bs4 import BeautifulSoup
ret=requests.get('https://www.shicimingju.com/book/hongloumeng.html')
# print(ret.text)
soup=BeautifulSoup(ret.text,'lxml')
li_list=soup.find(class_='book-mulu').find('ul').find_all('li')
with open('hlm.txt','w',encoding='utf-8') as f:
for li in li_list:
content=li.find('a').text
url='https://www.shicimingju.com'+li.find('a').get('href')
f.write(content)
f.write('
')
res_content=requests.get(url)
soup2=BeautifulSoup(res_content.text,'lxml')
content_detail=soup2.find(class_='chapter_content').text
f.write(content_detail)
f.write('
')
print(content,'写入了')
爬取肯德基门店
3 爬肯德基门店
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword
import requests
header = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
}
data = {
'cname': '',
'pid': 20,
'keyword': '浦东',
'pageIndex': 1,
'pageSize': 10
}
ret = requests.post('http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword', data=data, headers=header)
print(ret.json())
爬取糗事百科
4 爬糗事百科段子
#https://www.qiushibaike.com/text/page/2/
import requests
from bs4 import BeautifulSoup
ret=requests.get('https://www.qiushibaike.com/text/page/2/')
# print(ret.text)
soup=BeautifulSoup(ret.text,'html.parser')
article_list=soup.find_all(class_='article')
# print(article_list)
for article in article_list:
content=article.find(class_='content').text
print(content)
print('-------')
1 打码平台使用
1 不花钱破解验证码：数字字母的组合---》识别率一般
2 花钱---》复杂的验证码---》打码平台
-云打码
-超级鹰（以它为例，破解12306的）
2 selenium登录获得cookie，使用requests发送请求
# from selenium import webdriver
# import time
import json
# bro=webdriver.Chrome(executable_path='chromedriver.exe')
#
# bro.get('https://dig.chouti.com/')
# bro.maximize_window() # 最大化
# bro.implicitly_wait(10)
# login_btn=bro.find_element_by_link_text('登录')
# login_btn.click()
#
# name_input=bro.find_element_by_name('phone')
# password_input=bro.find_element_by_name('password')
# name_input.send_keys('18953675221')
# password_input.send_keys('lqz123')
#
# login_real_btn=bro.find_element_by_css_selector('button.login-btn')
# login_real_btn.click()
#
# # 可能有验证码
# time.sleep(10)
#
# cookie=bro.get_cookies()
#
# print(cookie)
# with open('cookie.json','w') as f:
# json.dump(cookie,f)
#
#
# print('cookie写入到文件中了')
# 自动点赞功能
import requests
from requests.cookies import RequestsCookieJar
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36',
'Referer': 'https://dig.chouti.com/',
# 'Cookie':'deviceId=web.eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJqaWQiOiIzZmMzMDcxMC1kYTE4LTRhYjEtODgyYi1jMjJiNDJmZGQ0M2MiLCJleHBpcmUiOiIxNjEyMzQwNDkxODkyIn0.-rOq71RiwftdV6hywRH7VU6mJLLHour4W8vd7R7VSjM; __snaker__id=5v8JU21SihPI5qPo; _9755xjdesxxd_=32; YD00000980905869%3AWM_TID=S1%2B5wnw84kpFRVFRBAJvePHwfuWOllVw; gdxidpyhxdE=qjBxjj9DZSdEqLP9dsw7LIaiVZt90hIoMIyY1uiz2NsZigVtqxoRGyr7R5PWhKHIr%2BkrBADuEa3%5CGNNRdJ2JMGzmtetESp%2BkeazmmQVeObtbcHO2Db%2FA%5CR06TGfdvarx%2BlvQO70UtX4zGkNaSUH1mXVNo%2BydlxLNxv72ivYgEgmga8ze%3A1611026700588; YD00000980905869%3AWM_NI=Q4TKzSEwfVhdRZu%2BqO0ALrTB9UwQsMFZV%2BtYYe4hp%2BZE32Uiv6uU0DtTfDxmHrV70D4hpmzh7G69jaXfVH9P3JbVycL4n1Dx5NFP%2BW7wOXo0y2ovpUQCCoxwld%2FRv4mzWWg%3D; YD00000980905869%3AWM_NIKE=9ca17ae2e6ffcda170e2e6eed7aa658fa789b4e244fb928bb2c14a879a9baaf541acbe8e8df173ab94e5bacf2af0fea7c3b92a93ec9cacf95987a9aab7eb709286bbccf445f49f8493d74afb8bb9b2f24786869accf7539bbbfc89f3219a9bfdd3d863b6eabbb6b350b88caaa5fb678cae9ad8b350f8b8c08ef964f599fadae96b9cba9aa9bc5cf196aeb7fc6990eca2d2c774f7928ab1aa5df5a981b9ee3cbbeea197f35f939d8d90fb7db0bce1b3f540afa699b8e637e2a3; token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJqaWQiOiJjZHVfNTMyMDcwNzg0NjAiLCJleHBpcmUiOiIxNjEzNjE3ODE2NDU5In0.lZVzlzVAtPkdg5guBx2ju8zILeOtAFrW7UTAnlf-Yfw; Hm_lvt_03b2668f8e8699e91d479d62bc7630f1=1609748496,1611025799,1611283275,1611286554; Hm_lpvt_03b2668f8e8699e91d479d62bc7630f1=1611286868'
}
res = requests.get('https://dig.chouti.com/link/hot', headers=header)
print(res.json())
jar=RequestsCookieJar()
# 从文件中读出来，写到cookie中
with open('cookie.json','r') as f:
cookie_l=json.load(f)
for cookie in cookie_l:
jar.set(cookie['name'], cookie['value'])
# cookie={}
for item in res.json()['data']:
id = item['id']
print(id)
# 点赞,缺cookie
data={
'linkId':id
}
res = requests.post('https://dig.chouti.com/link/vote', headers=header,cookies=jar,data=data)
# res = requests.post('https://dig.chouti.com/link/vote', headers=header,data=data)
print(res.text)
3 自动登录12306
from selenium import webdriver
import time
# import json
# bro=webdriver.Chrome(executable_path='./chromedriver')
# bro.get('https://dig.chouti.com/')
# # time.sleep(20)
# cookie=bro.get_cookies()
# print(cookie)
# with open('cookie.json','w') as f:
# json.dump(cookie,f)
import requests
import json
from requests.cookies import RequestsCookieJar
#这里我们使用cookie对象进行处理
jar = RequestsCookieJar()
with open("cookie.json", "r") as fp:
cookies = json.load(fp)
for cookie in cookies:
jar.set(cookie['name'], cookie['value'])
header={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36',
'Referer': 'http://dig.chouti.cc/',
}
data={
'linkId': 30268402
}
res=requests.post('http://dig.chouti.cc/link/vote',cookies=jar,headers=header,data=data)
print(res.text)
from selenium import webdriver
import time
#pillow
from PIL import Image
# 引入超级鹰
from chaojiying import Chaojiying_Client
from selenium.webdriver import ActionChains
bro=webdriver.Chrome(executable_path='./chromedriver.exe')
bro.implicitly_wait(10)
try:
bro.get('https://kyfw.12306.cn/otn/resources/login.html')
bro.maximize_window() # 窗口最大化，全屏
button_z=bro.find_element_by_css_selector('.login-hd-account a')
button_z.click()
time.sleep(2)
# 截取整个屏幕
bro.save_screenshot('./main.png')
# 验证码的位置和大小
img_t=bro.find_element_by_id('J-loginImg')
print(img_t.size)
print(img_t.location)
size=img_t.size
location=img_t.location
img_tu = (int(location['x']), int(location['y']), int(location['x'] + size['width']), int(location['y'] + size['height']))
# # 抠出验证码
# #打开
img = Image.open('./main.png')
# 抠图
fram = img.crop(img_tu)
# 截出来的小图
fram.save('code.png')
# 调用超级鹰破解
chaojiying = Chaojiying_Client('306334678', 'lqz12345', '903641') #用户中心>>软件ID 生成一个替换 96001
im = open('code.png', 'rb').read() #本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
# print(chaojiying.PostPic(im, 9004))
## 返回结果如果有多个 260,133|123，233,处理这种格式[[260,133],[123,233]]
res=chaojiying.PostPic(im, 9004)
print(res)
result=res['pic_str']
all_list = []
if '|' in result:
list_1 = result.split('|')
count_1 = len(list_1)
for i in range(count_1):
xy_list = []
x = int(list_1[i].split(',')[0])
y = int(list_1[i].split(',')[1])
xy_list.append(x)
xy_list.append(y)