Python爬虫常用函数大揭秘!

from bs4 import BeautifulSouphtml = "<html><body><h1>标题</h1></body></html>"soup = BeautifulSoup(html, 'html.parser')print(soup.h1.text)

html = '<div><span class="price">$99</span></div>'soup = BeautifulSoup(html, 'html.parser')price = soup.select('.price')[0].textprint(price)

import retext = "价格是：100元，优惠后是80元"prices = re.findall(r"\d+", text)print(prices)

import jsonjson_str = '{"name": "Tom", "age": 22}'data = json.loads(json_str)print(data['name'])

headers = {    "User-Agent": "Mozilla/5.0"}response = requests.get("https://httpbin.org/headers", headers=headers)print(response.text)

session = requests.Session()session.get("https://httpbin.org/cookies/set?name=value")res = session.get("https://httpbin.org/cookies")print(res.text)

from lxml import etreehtml = "<div><p>Hello</p><p>World</p></div>"tree = etree.HTML(html)text = tree.xpath("//p/text()")print(text)

import timefor i in range(3):    print(f"爬取第{i+1}页")    time.sleep(1)

try:    r = requests.get("http://bad.url")except requests.exceptions.RequestException as e:    print("请求出错：", e)