requests.request(method,url,**kwargs) # 常见参数 # params/data/json 上传数据 # files 上传文件 # headers/cookies # proxies # auth 授权
response = requests.get(url)
参数使用params传递，注意：不需要urlencode
data = {"wd": “北京”}
response = request.get(url, params=data)
response.text
response.encoding = ‘utf-8‘
response.url 获取请求的url
response.content
response.status_code
response.headers
response.json
response = requests.post(uri, data=data) #data上传的参数无需urlencode
同urllib.request的头定制
ua可以使用第三方包
from fake_useragent import UserAgent ua = UserAgent().random
在请求中设置proxies参数，参数类型是一个字典类型
import requests from fake_useragent import UserAgent url = ‘http://www.baidu.com/s‘ headers = { ‘user-agent‘: UserAgent().random } data = { ‘wd‘:‘ip‘ } proxy = { ‘http‘:‘219.149.59.250:9797‘ } r = requests.get(url=url,params=data,headers=headers,proxies=proxy) with open(‘proxy.html‘,‘w‘,encoding=‘utf-8‘) as fp: fp.write(r.text)
s = requests.session()
s.get() s.post() s.put() s.delete() s.patch() s.close() # 关闭会话 s.cookies # 获取cookies
XPath 是一门在 XML 文档中查找信息的语言。XPath 用于在 XML 文档中通过元素和属性进行导航。
/ 查找子节点，HTML中从<html>开始的 /html/title/text()
// 查找所有子孙节点，不考虑层级关系 如：//title/text()
./a/@href 当前路径下的a元素的href属性，如/html -> Element ， ./title/text()
../span/text() 父级下的span的文本内容
扩展：使用*通配符 /* 任意一个子节点，//*任意一个孙子节点
//div[@id] 查找所有包含id属性的div节点
//div[@id="maincontent"] 查询id属性为maincontent的div的标签
//@class 查询带有class属性的所有标签
//div[@id="head" and @class="s_down"] 查找所有id属性等于head并且class属性等于s_down的div标签 （多个条件，and且的关系，or或的关系）
//title | //price 同时获取title和price两个标签，| 前后的两个是完整且独立的xpath路径
//div[contains(@id, "he")] 查询所有id属性中包含he的div标签
//div[starts-with(@id, "he")] 查询所有id属性中包以he开头的div标签
//div[ends-with(@id, "he")] 查询所有id属性中包以he结尾的div标签
//ul/li[last()]/a/@href ul中最后一个li内的a元素的href属性值
//div/h1/text() 查找所有div标签下的直接子节点h1的内容
pip install lxml
chrome 安装xpath helper，ctrl+shift+x 打开控制台，Shift+选择网页内容
from lxml import etree
html_tree = etree.parse(‘XX.html‘) # 解析本地html文件
html_tree = etree.HTML(rsponse.read().decode(‘utf-8‘) # 解析网络的html字符串
xpath()返回是一个list列表
xpath返回的Element，可以看成是一个字典
import os import time from csv import DictWriter from random import random import requests from lxml import etree from fake_useragent import UserAgent has_header = os.path.exists("gushiwen.csv") # 是否第一次写入csv的头 header_fields = (‘title‘, ‘author‘, ‘content‘) def itemipeline4csv(item): # 保存数据 global has_header with open(‘gushiwen.csv‘, ‘a‘) as f: writer = DictWriter(f, header_fields) if not has_header: writer.writeheader() # 写入第一行标题 has_header = True writer.writerow(item) # 写入数据 def parse(html): root = etree.HTML(html) divs = root.xpath("//div[@class=‘left‘]/div[@class=‘sons‘]") item = {} for div in divs: item["title"] = div.xpath(".//p[1]//text()")[0] item["author"] = " ".join(div.xpath(".//p[2]/a/text()")) item["content"] = div.xpath(".//div[@class=‘contson‘]//text()") itemipeline4csv(item) def get(url): resp = requests.get(url, headers={‘User-Agent‘: UserAgent().random}) if resp.status_code == 200: parse(resp.text) else: raise Exception("请求失败") if __name__ == ‘__main__‘: for i in range(1, 11): time.sleep(random()) get("https://www.gushiwen.org/default_%s.aspx" % i)
补充：云打码使用了超级鹰第三方，注册账号重置，简单的修改，最后调用read_code()方法获取验证码的字符串
import requests from hashlib import md5 class Chaojiying_Client(object): def __init__(self, username, password, soft_id): self.username = username password = password.encode(‘utf8‘) self.password = md5(password).hexdigest() self.soft_id = soft_id self.base_params = { ‘user‘: self.username, ‘pass2‘: self.password, ‘softid‘: self.soft_id, } self.headers = { ‘Connection‘: ‘Keep-Alive‘, ‘User-Agent‘: ‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)‘, } def PostPic(self, im, codetype): """ im: 图片字节 codetype: 题目类型 参考 http://www.chaojiying.com/price.html """ params = { ‘codetype‘: codetype, } params.update(self.base_params) files = {‘userfile‘: (‘ccc.jpg‘, im)} r = requests.post(‘http://upload.chaojiying.net/Upload/Processing.php‘, data=params, files=files, headers=self.headers) return r.json() def ReportError(self, im_id): """ im_id:报错题目的图片ID """ params = { ‘id‘: im_id, } params.update(self.base_params) r = requests.post(‘http://upload.chaojiying.net/Upload/ReportError.php‘, data=params, headers=self.headers) return r.json() def read_code(filename): chaojiying = Chaojiying_Client(‘huiyichanmian‘, ‘christian825‘, ‘903878‘) # 用户中心>>软件ID 生成一个替换 96001 im = open(filename, ‘rb‘).read() # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要// ret = chaojiying.PostPic(im, 8001) return ret[‘pic_str‘]
""" 1、下载验证码的图片 2、图片验证码的打码 3、登录 4、获取个人的收藏信息 """ import requests from lxml import etree from fake_useragent import UserAgent # 创建一个session对象 from day2.chaojiying import read_code session = requests.session() # 获取验证码的接口和登录的接口必须在同一个session中请求 def download_code(): resp = session.get(‘https://so.gushiwen.org/RandCode.ashx‘, headers={‘User-Agent‘: UserAgent(verify_ssl=False).random}) with open("code.png", ‘wb‘) as f: f.write(resp.content) def get_code_str(): download_code() return read_code("code.png") def login(): resp = session.post("https://so.gushiwen.org/user/login.aspx", data={ ‘email‘: ‘huiyichanmian@yeah.net‘, ‘pwd‘: ‘christian825‘, ‘code‘: get_code_str() }) if resp.status_code == 200: collect() else: print("-"*30) print(resp.text) def collect(): resp = session.get(‘https://so.gushiwen.org/user/collect.aspx‘) parse(resp.text) def parse(html): root = etree.HTML(html) divs = root.xpath("//div[@class=‘left‘]/div[@class=‘sons‘]") item = {} for div in divs: item["title"] = div.xpath(".//p[1]//text()")[0] item["author"] = " ".join(div.xpath(".//p[2]/a/text()")) item["content"] = div.xpath(".//div[@class=‘contson‘]//text()") print(item) if __name__ == ‘__main__‘: login()
原文：https://www.cnblogs.com/huiyichanmian/p/12456691.html
