5

pyGTrends 似乎不起作用。在 Python 中给出错误。

pyGoogleTrendsCsvDownloader 似乎可以工作，登录，但在收到 1-3 个请求（每天！）后抱怨配额用尽，即使使用相同的登录名/IP 手动下载也可以完美运行。

底线：两者都不起作用。通过stackoverflow搜索：人们试图从谷歌中提取csv的许多问题，但我找不到可行的解决方案......

提前感谢您：谁能提供帮助。代码应该怎么改？您知道另一种可行的解决方案吗？

这是 pyGoogleTrendsCsvDownloader.py 的代码

import httplib
import urllib
import urllib2
import re
import csv
import lxml.etree as etree
import lxml.html as html
import traceback
import gzip
import random
import time
import sys

from cookielib import Cookie, CookieJar
from StringIO import StringIO


class pyGoogleTrendsCsvDownloader(object):
'''
Google Trends Downloader
Recommended usage: 
from pyGoogleTrendsCsvDownloader import pyGoogleTrendsCsvDownloader
r = pyGoogleTrendsCsvDownloader(username, password)
r.get_csv(cat='0-958', geo='US-ME-500')
'''
def __init__(self, username, password):
    '''  
Provide login and password to be used to connect to Google Trends
All immutable system variables are also defined here
'''

    # The amount of time (in secs) that the script should wait before making a request.
    # This can be used to throttle the downloading speed to avoid hitting servers too hard.
    # It is further randomized.
    self.download_delay = 0.25

    self.service = "trendspro"
    self.url_service = "http://www.google.com/trends/"
    self.url_download = self.url_service + "trendsReport?"

    self.login_params = {}
    # These headers are necessary, otherwise Google will flag the request at your account level
    self.headers = [('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:12.0) Gecko/20100101 Firefox/12.0'),
                    ("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"),
                    ("Accept-Language", "en-gb,en;q=0.5"),
                    ("Accept-Encoding", "gzip, deflate"),
                    ("Connection", "keep-alive")]
    self.url_login = 'https://accounts.google.com/ServiceLogin?service='+self.service+'&passive=1209600&continue='+self.url_service+'&followup='+self.url_service
    self.url_authenticate = 'https://accounts.google.com/accounts/ServiceLoginAuth'
    self.header_dictionary = {}

    self._authenticate(username, password)

def _authenticate(self, username, password):
    '''
Authenticate to Google:
1 - make a GET request to the Login webpage so we can get the login form
2 - make a POST request with email, password and login form input values
'''

    # Make sure we get CSV results in English
    ck = Cookie(version=0, name='I4SUserLocale', value='en_US', port=None, port_specified=False, domain='www.google.com', domain_specified=False,domain_initial_dot=False, path='/trends', path_specified=True, secure=False, expires=None, discard=False, comment=None, comment_url=None, rest=None)

    self.cj = CookieJar()
    self.cj.set_cookie(ck)
    self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cj))
    self.opener.addheaders = self.headers

    # Get all of the login form input values
    find_inputs = etree.XPath("//form[@id='gaia_loginform']//input")
    try:
        #
        resp = self.opener.open(self.url_login)

        if resp.info().get('Content-Encoding') == 'gzip':
            buf = StringIO( resp.read())
            f = gzip.GzipFile(fileobj=buf)
            data = f.read()
        else:
            data = resp.read()

        xmlTree = etree.fromstring(data, parser=html.HTMLParser(recover=True, remove_comments=True))

        for input in find_inputs(xmlTree):
            name = input.get('name')
            if name:
                name = name.encode('utf8')
                value = input.get('value', '').encode('utf8')
                self.login_params[name] = value
    except:
        print("Exception while parsing: %s\n" % traceback.format_exc())

    self.login_params["Email"] = username
    self.login_params["Passwd"] = password

    params = urllib.urlencode(self.login_params)
    self.opener.open(self.url_authenticate, params)

def get_csv(self, throttle=False, **kwargs):
    '''
Download CSV reports
'''

    # Randomized download delay
    if throttle:
        r = random.uniform(0.5 * self.download_delay, 1.5 * self.download_delay)
        time.sleep(r)

    params = {
        'export': 1
    }
    params.update(kwargs)
    params = urllib.urlencode(params)

    r = self.opener.open(self.url_download + params)

    # Make sure everything is working ;)
    if not r.info().has_key('Content-Disposition'):
        print "You've exceeded your quota. Continue tomorrow..."
        sys.exit(0)

    if r.info().get('Content-Encoding') == 'gzip':
        buf = StringIO( r.read())
        f = gzip.GzipFile(fileobj=buf)
        data = f.read()
    else:
        data = r.read()

    myFile = open('trends_%s.csv' % '_'.join(['%s-%s' % (key, value) for (key, value) in kwargs.items()]), 'w')
    myFile.write(data)
    myFile.close()
4

2 回答 2

3

虽然我不知道python，但我可能有一个解决方案。我目前在 C# 中做同样的事情，虽然我没有得到 .csv 文件，但我通过代码创建了一个自定义 URL，然后下载了该 HTML 并保存到一个文本文件（也通过代码）。在这个 HTML 中（第 12 行）是创建用于 Google 趋势的图表所需的所有信息。然而，这里面有很多不必要的文本需要删减。但无论哪种方式，你最终都会得到相同的结果。谷歌趋势数据。我在这里发布了对我的问题的更详细的答案：

从 Google 趋势下载 .csv 文件

于 2016-11-21T20:22:54.143 回答
1

有一个名为 pytrends 的替代模块 - https://pypi.org/project/pytrends/真的很酷。我会推荐这个。

示例用法：

import numpy as np
import pandas as pd                        
from pytrends.request import TrendReq
pytrend = TrendReq()

#It is the term that you want to search
pytrend.build_payload(kw_list=["Eminem is the Rap God"])

# Find which region has searched the term
df = pytrend.interest_by_region()
df.to_csv("path\Eminem_InterestbyRegion.csv")

如果您有要搜索的术语列表，您可以使用“for 循环”根据您的意愿自动执行洞察。

于 2021-02-04T12:57:52.397 回答