Python 抓取微信公众号账号信息的方法

import requests as req
import re
reTypes = r'id="pc_\d*" uigs="(pc_\d*)">([\s\S]*?)</a>'
Entry = "http://weixin.sogou.com/"
entryPage = req.get(Entry)
allTypes = re.findall(reTypes, getUTF8(entryPage))
for (pcid, category) in allTypes:
  for page in range(1, 100):
    url = 'http://weixin.sogou.com/pcindex/pc/{}/{}.html'.format(pcid, page)
    print(url)
    categoryList = req.get(url)
    if categoryList.status_code != 200:
      break

reProfile = r'<li id[\s\S]*?<a href="([\s\S]*?)" rel="external nofollow" '
allProfiles = re.findall(reOAProfile, getUTF8(categoryList))
for profile in allProfiles:
  profilePage = req.get(profile)
  if profilePage.status_code != 200:
    continue

from flask import g, Flask, render_template
import sqlite3
app = Flask(__name__)
DATABASE = "./db/wx.db"
def get_db():
  db = getattr(g, '_database', None)
  if db is None:
    db = g._database = sqlite3.connect(DATABASE)
  return db
@app.teardown_appcontext
def close_connection(exception):
  db = getattr(g, '_database', None)
  if db is not None:
    db.close()
@app.route("/<int:page>")
@app.route("/")
def hello(page=0):
  cur = get_db().cursor()
  cur.execute("SELECT * FROM wxoa LIMIT 30 OFFSET ?", (page*30, ))
  rows = []
  for row in cur.fetchall():
    rows.append(row)
  return render_template("app.html", wx=rows, cp=page)
if __name__ == "__main__":
  app.run(debug=True, port=8000)