[Journey] 1 million UVs/month in 12 months using AI generated content. Let's do it!
- Thread starter Sartre
- Start date
- Status
Sartre
Ignored a dispute resolution thread against them.
- Apr 1, 2010
- 1,672
- 4,573
Do you know an easy solution for the MITM mapping?you can use a MITM to map their private api. is quillbot only one with this? does anyone now if rytr or wordtune has a private api too? could find the routes easily, only problem if you consume too much they'll see the requests in their servers and might wonder why ip addresses that aren't internal are consuming so much of these endpoints
Both Quillbot and Wordtune ratelimit you if you paraphrase all day even though they say they are unlimited. I tested with Selenium.
dlyhai
Elite Member
- May 31, 2015
- 3,499
- 513
Is Selenium good?
Sartre
Ignored a dispute resolution thread against them.
- Apr 1, 2010
- 1,672
- 4,573
Never seen anything like that unfortunatelyWow dude, your tool is definitely awesome, do you know any paid tool that does the same as yours? i'm very much interested in getting my hand on one of these because my lazy ass can't really write articles
I'd gladly pay cause we invested a lot of time and money already into this and would be cool to avoid it.
- Sep 25, 2013
- 4,705
- 2,701
@Sartre How long until you usually start getting clicks from Google/Bing to your brand new websites? & How long until they reach 100 clicks, etc? I got a similar site running for almost 2 months now with about 2000 posts and its getting only a few clicks a day, dunno if I should interpret it as lack of quality in the articles/AI or simply too soon.
I'll take a look at it later. But via api might need private key or rate limit. unless only they call in it might not be throttled. Need to check.
When you say you tested with selenium, do you mean they rate limited you or literally with rotating to a unique instance everything they still rate limited the app internally?
has anyone tested https://paraphrasetool.com/ ?
Sartre
Ignored a dispute resolution thread against them.
- Apr 1, 2010
- 1,672
- 4,573
definitely something is wrong I'm getting clicks within days, 100 daily clicks within 2 weeks of posting 1000 articles last website. Maybe you're choosing the wrong keywords too.
neither quillbot nor wordtune have a public API.
they rate limit internally. I talked with both owners too during video calls, they were interested in my use case
it's really bad.
- Sep 25, 2013
- 4,705
- 2,701
MIght be the keywords I'm not too sure. My domain is also brand new though, not expired and no backlinks etc... I assume that might affect how soon till it starts ranking and bringing in traffic
The way I do for keywords is I mass scrape google auto suggest then run it through google keyword planner and export all keywords getting 50-5000 clicks per months and that's the keywords I enter into my AI Program.
My current Program does the following:
- Google's the keyword
- Withdraws H2's & the text underneath from different URLs
- Once it has 4-5 H2's + text it stops this part
- Paraphrases the text underneath the H2's with Pegasus Paraphraser
- Uploads to Wordpress with a generic image as header (related to the niche but only have 5-6 different images to choose from so when posting 2000 articles ends up having a lot of posts with the same image)
- Sep 25, 2013
- 4,705
- 2,701
Question for you @Sartre
How does your AI know when to double breakline?
Like this.
An Issue I have with my current one is that under the H2's if the text is big it'll just be one big wall of text until the next H2 with no spaces between each paragraph. I'm not too sure how to make my AI figure out when the next Phrase is meant to be a whole new paragraph or not.
How does your AI know when to double breakline?
Like this.
An Issue I have with my current one is that under the H2's if the text is big it'll just be one big wall of text until the next H2 with no spaces between each paragraph. I'm not too sure how to make my AI figure out when the next Phrase is meant to be a whole new paragraph or not.
neOtron
Power Member
- Nov 22, 2012
- 512
- 630
I had the same issue. refer to this post of mine https://www.blackhatworld.com/seo/j...tent-lets-do-it.1360940/page-18#post-15108278
the mentioned libraries will help convert your unsegmented text to segmented texts. although determining paragraphs wont really be possible but atleast it helps alot in determining the end of each sentence. and then i randomly split the 4-8 sentences in paragraphs.
If you find a better solution please let me know too
- Sep 25, 2013
- 4,705
- 2,701
GotchaI had the same issue. refer to this post of mine https://www.blackhatworld.com/seo/j...tent-lets-do-it.1360940/page-18#post-15108278
the mentioned libraries will help convert your unsegmented text to segmented texts. although determining paragraphs wont really be possible but atleast it helps alot in determining the end of each sentence. and then i randomly split the 4-8 sentences in paragraphs.
If you find a better solution please let me know too
Fortunately haven't had that issue with commas, etc.The way I extract everything and paraphrase doesn't really delete anything. It's mostly just the paragraph thing.
Shaybib
Senior Member
- Mar 23, 2018
- 831
- 262
When you scrape you scrape text that is in paragraphs why can't you maintain those paragraphs?
neOtron
Power Member
- Nov 22, 2012
- 512
- 630
depends on where you are scraping texts from. i m not scraping from other webites .so i have to deals with alot of unsegmented texts
- Sep 25, 2013
- 4,705
- 2,701
Because newspaper3k is what I use and it returns everything with no paragraphs iirc. And when I paraphrase I lose the paragraphs too
Shaybib
Senior Member
- Mar 23, 2018
- 831
- 262
So use bs4 and paraphrase every paragraph separately. What is newspaper advantage over bs4?
Sartre
Ignored a dispute resolution thread against them.
- Apr 1, 2010
- 1,672
- 4,573
you're using it wrong. newspaper3k returns paraphraphs. look into the tutorial
- Sep 25, 2013
- 4,705
- 2,701
You're right, newspaper3k does have the paragraphs, they're just lost when I run my code through NLTK to separate the text into sentences so I can paraphrase, that's when the paragraphs are lost.
Think I may have figured out how to fix this now that u both called it out lol
- Status