import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
#from pymongo import MongoClient
import jieba
import wordcloud
base_url = 'https://m.weibo.cn/api/container/getIndex?'
headers = {
#'Host': 'm.weibo.cn',
'Referer': 'https://m.weibo.cn/u/6390210715',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
'X-Requested-With': 'XMLHttpRequest',
}
#client = MongoClient()
#db = client['weibo']
#collection = db['weibo']
max_page = 20
def get_page(page):
params = {
'type': 'uid',
'value': '6390210715',
'containerid': '1076036390210715',
'page': page
}
url = base_url + urlencode(params)
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.json(), page
except requests.ConnectionError as e:
print('Error', e.args)
list1=[]
def parse_page(json, page: int):
if json:
items = json.get('data').get('cards')
for index, item in enumerate(items):
if page == 1 and index == 1:
continue
else:
item = item.get('mblog', {})
weibo = {}
list2=[]
#weibo['id'] = item.get('id')
weibo[''] = pq(item.get('text')).text()
list2.append(pq(item.get('text')).text())
#weibo['attitudes'] = item.get('attitudes_count')
#weibo['comments'] = item.get('comments_count')
#weibo['reposts'] = item.get('reposts_count')
list1.append(list2)
yield weibo
#def save_to_mongo(result):
# if collection.insert(result):
# print('Saved to Mongo')
def writefile():
for item in list1:
with open('weibo2.txt', mode='a', encoding='utf-8') as f:
f.write('%s\n' % (item))
def wordCloud():
m = open('weibo2.txt', mode='r', encoding='utf-8')
t = m.read()
ls = jieba.lcut(t)
m.close()
txt = " ".join(ls)
w = wordcloud.WordCloud(font_path="msyh.ttc", width=1000, height=700, max_words=25)
w.generate(txt)
w.to_file("myweibo.png")
if __name__ == '__main__':
for page in range(1, max_page + 1):
json = get_page(page)
results = parse_page(*json)
for result in results:
print(result)
writefile()
wordCloud()